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

    Neuronpedia

    INDEX
    Explanations

    binary digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rosso
    -0.06
    _flags
    -0.06
     dividend
    -0.06
     Natalie
    -0.06
     Něk
    -0.06
     finalist
    -0.06
    _Num
    -0.06
     Shard
    -0.06
     architectures
    -0.06
     kvinnor
    -0.05
    POSITIVE LOGITS
    。
    0.07
    。',↵
    0.07
    5
    0.07
     '&'
    0.07
    ить
    0.07
    100
    0.06
     Disconnect
    0.06
    &amp
    0.06
    について
    0.06
    $http
    0.06
    Act Density 0.002%

    No Known Activations