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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     longing
    -0.07
     initial
    -0.07
     Aussie
    -0.07
    мель
    -0.06
    няется
    -0.06
    icle
    -0.06
     px
    -0.06
     juin
    -0.06
    .initial
    -0.06
    [end
    -0.06
    POSITIVE LOGITS
    documentation
    0.08
    (InputStream
    0.07
    Forg
    0.06
    .truth
    0.06
    действ
    0.06
    .tagName
    0.06
    .actor
    0.06
    방
    0.06
    _USART
    0.06
     (=
    0.06
    Act Density 0.005%

    No Known Activations