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

    Neuronpedia

    INDEX
    Explanations

    pr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    957
    -0.07
    -------------
    -0.07
     Sweden
    -0.06
    _more
    -0.06
     Comparison
    -0.06
    联合
    -0.06
    Sweden
    -0.06
    _point
    -0.06
    Adjust
    -0.06
    ione
    -0.06
    POSITIVE LOGITS
    emmel
    0.07
    faker
    0.06
     thunk
    0.06
    isay
    0.06
     гра
    0.06
    .normal
    0.06
     ServiceException
    0.06
     پل
    0.06
     专
    0.06
     підприємств
    0.06
    Act Density 0.003%

    No Known Activations