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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alsa
    -0.08
    ISTIC
    -0.07
    _Char
    -0.07
    ช
    -0.07
    ケース
    -0.07
    TINGS
    -0.06
     Tas
    -0.06
    -than
    -0.06
     serotonin
    -0.06
    ayas
    -0.06
    POSITIVE LOGITS
     cał
    0.07
     Weiter
    0.06
    _conversion
    0.06
     decltype
    0.06
    íl
    0.06
     dostal
    0.06
    vature
    0.06
    арь
    0.06
    <?>
    0.06
    esimal
    0.06
    Act Density 0.051%

    No Known Activations