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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .are
    -0.07
    .isDefined
    -0.07
    itur
    -0.07
    ujet
    -0.07
     REAL
    -0.06
     parseInt
    -0.06
    _small
    -0.06
     purpos
    -0.06
     siege
    -0.06
     interchangeable
    -0.06
    POSITIVE LOGITS
    izmet
    0.07
     —↵
    0.06
    oad
    0.06
    衆
    0.06
    .TAG
    0.06
     rejo
    0.06
    _hresult
    0.06
    ırak
    0.06
     كم
    0.06
     kişinin
    0.06
    Act Density 0.004%

    No Known Activations