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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inclu
    -0.08
    �
    -0.07
     posto
    -0.07
     hat
    -0.07
     бок
    -0.06
     guards
    -0.06
    formula
    -0.06
     magnificent
    -0.06
     vape
    -0.06
     ':
    -0.06
    POSITIVE LOGITS
     ltd
    0.07
     hovering
    0.07
    >Action
    0.06
    $values
    0.06
    rix
    0.06
    ionales
    0.06
    ющ
    0.06
    .APP
    0.06
    INS
    0.06
     Network
    0.06
    Act Density 0.076%

    No Known Activations