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

    Neuronpedia

    INDEX
    Explanations

    phrases related to good or bad news

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

    discussions of good news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     use
    -0.36
     activity
    -0.31
     of
    -0.30
     Howell
    -0.29
    findBy
    -0.28
     snippetHide
    -0.28
     Horne
    -0.27
    iert
    -0.27
    áro
    -0.27
     Ing
    -0.27
    POSITIVE LOGITS
     للمعارف
    0.69
    rungsseite
    0.64
     فريبيس
    0.63
    ⮕
    0.62
    withIdentifier
    0.61
    RenderAtEndOf
    0.60
    حوالہ
    0.59
    EndInit
    0.58
     createState
    0.56
    flashdata
    0.56
    Act Density 0.007%

    No Known Activations