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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enez
    -0.07
    sudo
    -0.06
    .JComboBox
    -0.06
    ango
    -0.06
    альной
    -0.06
    istle
    -0.06
    fen
    -0.06
     İran
    -0.06
    enderror
    -0.06
    Resolve
    -0.06
    POSITIVE LOGITS
    าณาจ
    0.07
    310
    0.07
     cites
    0.07
    _RC
    0.06
     населения
    0.06
    /port
    0.06
    terdam
    0.06
    ï
    0.06
     (↵
    0.06
     deploy
    0.06
    Act Density 0.033%

    No Known Activations