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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ADC
    -0.07
    Batman
    -0.07
     評
    -0.07
    -under
    -0.06
    (session
    -0.06
     novelty
    -0.06
    تان
    -0.06
    inski
    -0.06
     робот
    -0.06
     παιδ
    -0.06
    POSITIVE LOGITS
     spíše
    0.06
     Admission
    0.06
    (wx
    0.06
    Dll
    0.06
    =UTF
    0.06
     đấu
    0.06
     punctuation
    0.06
    Fld
    0.06
    θμ
    0.06
     Organ
    0.06
    Act Density 0.082%

    No Known Activations