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

    Neuronpedia

    INDEX
    Explanations

    code and special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dojo
    -0.07
    (define
    -0.07
    wcs
    -0.06
     initializes
    -0.06
    726
    -0.06
    ',"
    -0.06
     Cbd
    -0.06
    _TARGET
    -0.06
    .Ο
    -0.06
     Kor
    -0.06
    POSITIVE LOGITS
    ого
    0.06
    Charlotte
    0.06
    щ
    0.06
    DIS
    0.06
    ┬
    0.06
    0.06
    hen
    0.06
    ガ
    0.06
    _form
    0.06
    诚
    0.06
    Act Density 0.001%

    No Known Activations