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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     throat
    -0.06
     QCOMPARE
    -0.06
    .getHours
    -0.06
    _smart
    -0.06
     NSInteger
    -0.06
    .splitext
    -0.06
    .LENGTH
    -0.06
    及び
    -0.06
    цій
    -0.06
    POSITIVE LOGITS
    checking
    0.07
    enne
    0.07
     porter
    0.07
    _sprite
    0.06
    EB
    0.06
    _profile
    0.06
    sock
    0.06
    date
    0.06
     prevalent
    0.06
    iloc
    0.06
    Act Density 0.000%

    No Known Activations