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

    Neuronpedia

    INDEX
    Explanations

    dim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .flag
    -0.08
    <form
    -0.07
    unched
    -0.07
    Fed
    -0.07
    joined
    -0.07
    _salt
    -0.07
    改制
    -0.07
    ธนา
    -0.07
     clumsy
    -0.06
    olec
    -0.06
    POSITIVE LOGITS
    قس
    0.08
     Они
    0.07
    _remote
    0.06
     worldwide
    0.06
     SH
    0.06
    �
    0.06
     episode
    0.06
    0.06
     것으로
    0.06
     Rh
    0.06
    Act Density 0.003%

    No Known Activations