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

    Neuronpedia

    INDEX
    Explanations

    Stop words/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TokenType
    -0.07
    .interface
    -0.06
     Fig
    -0.06
     utilities
    -0.06
    워
    -0.06
     webcam
    -0.06
     bus
    -0.06
     APC
    -0.06
    _roles
    -0.06
    込み
    -0.06
    POSITIVE LOGITS
    plies
    0.06
     tutar
    0.06
    uiten
    0.06
    ların
    0.06
     sure
    0.06
    _sidebar
    0.06
    ؛
    0.06
     lä
    0.06
    \data
    0.06
    -auth
    0.06
    Act Density 0.246%

    No Known Activations