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

    Neuronpedia

    INDEX
    Explanations

    Math formulas/expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     список
    -0.07
    _INTER
    -0.07
    /sdk
    -0.07
    厂房
    -0.07
    HOOK
    -0.07
    ễn
    -0.07
     tend
    -0.07
    .speed
    -0.07
     glean
    -0.07
     данных
    -0.06
    POSITIVE LOGITS
     Rew
    0.07
     الديمقرا
    0.07
    atchet
    0.07
    一步一步
    0.07
    eceğini
    0.06
     validations
    0.06
     zobowiąz
    0.06
    .setOnItemClickListener
    0.06
    .newLine
    0.06
     policym
    0.06
    Act Density 0.012%

    No Known Activations