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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $url
    -0.06
    _TW
    -0.06
     oppos
    -0.06
    ি�
    -0.06
    猛
    -0.06
    -auth
    -0.06
    /／
    -0.06
     referenced
    -0.06
     circa
    -0.06
    UnitOfWork
    -0.06
    POSITIVE LOGITS
    =float
    0.07
     中国
    0.07
     backbone
    0.07
    میر
    0.06
    ków
    0.06
    People
    0.06
    recio
    0.06
     dominated
    0.06
     undoubtedly
    0.06
    UCCEEDED
    0.06
    Act Density 0.001%

    No Known Activations