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

    Neuronpedia

    INDEX
    Explanations

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    criteria
    -0.09
     criteria
    -0.09
     disput
    -0.08
    alẹ
    -0.08
     Hierbij
    -0.08
    ाउँ
    -0.08
     iu
    -0.08
    ={(
    -0.08
     discrep
    -0.08
    ajo
    -0.08
    POSITIVE LOGITS
     annoyance
    0.09
     refreshments
    0.09
     студент
    0.08
    seh
    0.08
    _REAL
    0.08
     ছাত্র
    0.08
     annoy
    0.08
    .pause
    0.08
    .runtime
    0.08
     öğr
    0.08
    Act Density 0.005%

    No Known Activations