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

    Neuronpedia

    INDEX
    Explanations

    Timestamps and transcription

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knots
    -0.07
    446
    -0.06
    yd
    -0.06
     Isles
    -0.06
     годы
    -0.06
     那
    -0.06
     gần
    -0.06
    ác
    -0.06
     воду
    -0.06
    _logger
    -0.06
    POSITIVE LOGITS
    Packet
    0.07
     jur
    0.06
     vape
    0.06
     cripp
    0.06
     Vol
    0.06
    istency
    0.06
    ималь
    0.06
     string
    0.06
    @show
    0.06
    :string
    0.06
    Act Density 0.008%

    No Known Activations