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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eming
    -0.06
     �
    -0.06
    getitem
    -0.06
    /comment
    -0.06
    .combine
    -0.06
     getpid
    -0.06
    .booking
    -0.06
    >*/↵
    -0.06
     explosion
    -0.06
    VALUES
    -0.06
    POSITIVE LOGITS
     nieuwe
    0.07
    百
    0.07
     ринку
    0.07
    wang
    0.07
    ер
    0.06
    (rules
    0.06
     payloads
    0.06
    _COMPARE
    0.06
    elle
    0.06
     Enterprise
    0.06
    Act Density 0.041%

    No Known Activations