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

    Neuronpedia

    INDEX
    Explanations

    take

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ocur
    -0.06
     Influ
    -0.06
    .***
    -0.06
    ())),↵
    -0.06
     checkbox
    -0.06
    canvas
    -0.06
     impair
    -0.06
     Trying
    -0.06
    yro
    -0.06
     ступ
    -0.06
    POSITIVE LOGITS
    -note
    0.07
     takes
    0.07
    -terrorism
    0.07
    _REMOVE
    0.06
     Nature
    0.06
    meyen
    0.06
    οι
    0.06
    opsy
    0.06
     nhân
    0.06
    lica
    0.06
    Act Density 0.034%

    No Known Activations