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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PROFITS
    -0.06
    ritos
    -0.06
    adeon
    -0.06
    谈
    -0.06
    ohan
    -0.06
    ul
    -0.06
    noop
    -0.06
    سوب
    -0.06
     acquitted
    -0.06
    plen
    -0.06
    POSITIVE LOGITS
     хв
    0.08
     exh
    0.07
    );
↵
    0.07
     ordered
    0.06
    ")){
↵
    0.06
    )>
    0.06
    "testing
    0.06
     �
    0.06
    .articles
    0.06
     Комп
    0.06
    Act Density 0.002%

    No Known Activations