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

    Neuronpedia

    INDEX
    Explanations

    start tokens or markers indicating the beginning of sections or key segments in the text

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

    news and code segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.76
    Tikang
    -0.73
    Gambas
    -0.70
     дописавши
    -0.65
    THISDAY
    -0.63
    raught
    -0.60
    MethodManager
    -0.59
    انيف
    -0.58
    PyExc
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    POSITIVE LOGITS
     features
    0.53
     gameplay
    0.52
     Free
    0.51
     thrilling
    0.50
    Free
    0.48
     action
    0.48
     storyline
    0.48
     Features
    0.48
     realism
    0.47
     cho
    0.47
    Act Density 0.027%

    No Known Activations