Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and parameters related to programming and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    data sending, destination airport, next slide, foreign message, ambient light, driver/passenger side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مصادر
    -0.85
    findpost
    -0.79
     الحره
    -0.69
    IVEREF
    -0.68
    GEBURTSDATUM
    -0.66
    aarrggbb
    -0.66
    rungsseite
    -0.64
     financières
    -0.64
     nuages
    -0.63
    utilisons
    -0.61
    POSITIVE LOGITS
    ſelf
    0.73
    neſs
    0.71
    醐
    0.67
     leaſt
    0.57
    ſelves
    0.57
     Sra
    0.56
    '@
    0.56
     CLS
    0.54
    یرات
    0.54
    wiſe
    0.54
    Act Density 0.157%

    No Known Activations