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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to terms and conditions regarding changes and updates

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

    future changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.58
    apatalk
    -0.52
    OrBuilder
    -0.51
    IGraphics
    -0.50
    awakeFromNib
    -0.49
    pperware
    -0.48
    apnews
    -0.48
    UserScript
    -0.47
     Raton
    -0.47
    ImageContext
    -0.46
    POSITIVE LOGITS
     changes
    0.47
    changes
    0.43
     변경
    0.40
     change
    0.38
     Changes
    0.38
     futuros
    0.37
     prossimo
    0.35
    toprule
    0.35
     CHANGES
    0.34
     futuras
    0.34
    Act Density 0.011%

    No Known Activations