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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resolves
    -0.07
    Ascending
    -0.07
    例
    -0.07
    щество
    -0.07
    );

↵
    -0.07
    ढ
    -0.06
    ';
↵
↵
    -0.06
    ，比
    -0.06
     lô
    -0.06
    "]:
    -0.06
    POSITIVE LOGITS
     debt
    0.07
     Newport
    0.06
     marsh
    0.06
     Bu
    0.06
     उद
    0.06
     стан
    0.06
    _PCM
    0.06
     transmissions
    0.06
    -bootstrap
    0.06
     �
    0.06
    Act Density 0.001%

    No Known Activations