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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ührung
    -0.07
    Inverse
    -0.07
    _crossentropy
    -0.06
    bg
    -0.06
     Irving
    -0.06
     toutes
    -0.06
    罪
    -0.06
    USART
    -0.06
    .intent
    -0.06
    chemy
    -0.06
    POSITIVE LOGITS
     insecurity
    0.07
     clinical
    0.07
    歲
    0.07
     Jama
    0.07
    lâm
    0.07
    켓
    0.06
     einem
    0.06
     Wow
    0.06
     кілька
    0.06
     kombin
    0.06
    Act Density 0.048%

    No Known Activations