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

    Neuronpedia

    INDEX
    Explanations

    holders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emergence
    -0.07
     Voters
    -0.07
     Contrib
    -0.06
    .reduce
    -0.06
     fibre
    -0.06
     Vatican
    -0.06
    .Formatting
    -0.06
    括
    -0.06
    endi
    -0.06
     Friends
    -0.06
    POSITIVE LOGITS
     KR
    0.06
    куля
    0.06
    UserName
    0.06
    peon
    0.06
    Зап
    0.06
    91
    0.06
    객
    0.06
     mek
    0.06
    IconButton
    0.06
    fl
    0.06
    Act Density 0.003%

    No Known Activations