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

    Neuronpedia

    INDEX
    Explanations

    school grades

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enties
    -0.06
    utors
    -0.06
    UTC
    -0.06
    title
    -0.06
    _WRITE
    -0.06
    .setFont
    -0.06
    =d
    -0.06
    travel
    -0.06
    (suite
    -0.06
     Indices
    -0.06
    POSITIVE LOGITS
     served
    0.07
    وح
    0.07
     obe
    0.06
    евой
    0.06
     prostitut
    0.06
     assists
    0.06
    stacles
    0.06
     Piet
    0.06
    ujte
    0.06
     respondents
    0.06
    Act Density 0.007%

    No Known Activations