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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -suite
    -0.06
    цов
    -0.06
     masa
    -0.06
    radius
    -0.06
     Pew
    -0.06
    lendir
    -0.06
     Gala
    -0.06
     comma
    -0.06
    );

↵
    -0.06
    .tokenize
    -0.06
    POSITIVE LOGITS
    客户
    0.08
     restoring
    0.07
     inconsistency
    0.07
    ایش
    0.07
    已经
    0.06
     Small
    0.06
     Ethan
    0.06
    (__
    0.06
    mmm
    0.06
     randomly
    0.06
    Act Density 0.000%

    No Known Activations