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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Eval
    -0.07
     labels
    -0.07
     �
    -0.06
     perse
    -0.06
    AI
    -0.06
    shutdown
    -0.06
    .ReadByte
    -0.06
    .symmetric
    -0.06
    BorderColor
    -0.06
     advertiser
    -0.06
    POSITIVE LOGITS
    /screen
    0.07
    /ss
    0.06
     Tep
    0.06
    _numer
    0.06
     Prahy
    0.06
    ll
    0.06
     NM
    0.06
     tên
    0.06
     м
    0.06
    *out
    0.06
    Act Density 0.062%

    No Known Activations