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

    Neuronpedia

    INDEX
    Explanations

    words related to materials and qualities

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

    Code, file paths, and symbols

    np_acts-logits-general · gemini-2.0-flash

    stainless steel, flashing lights, step ahead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.77
    ագրություններ
    -0.76
     particularmente
    -0.67
     antaranya
    -0.60
     дописавши
    -0.60
     particularly
    -0.59
    /**
    -0.59
     especially
    -0.59
     nemlig
    -0.58
    rophes
    -0.58
    POSITIVE LOGITS
    -/
    0.65
    CMAKE
    0.53
     multi
    0.52
    beyaz
    0.52
    /
    0.51
    dized
    0.51
    +/
    0.51
    raszamy
    0.51
    (?)
    0.50
    ített
    0.50
    Act Density 0.267%

    No Known Activations