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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    シリーズ
    -0.07
    anela
    -0.07
    histor
    -0.07
     serie
    -0.07
     //{
    -0.07
    LOUD
    -0.07
    éis
    -0.06
    ouri
    -0.06
     tut
    -0.06
     Place
    -0.06
    POSITIVE LOGITS
     польз
    0.06
    =forms
    0.06
     contention
    0.06
     beef
    0.06
     detects
    0.06
     rewarded
    0.05
     voor
    0.05
     inconsistent
    0.05
    รว
    0.05
     [_
    0.05
    Act Density 0.002%

    No Known Activations