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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Programming
    -0.07
    腕
    -0.07
     contrato
    -0.06
     деятель
    -0.06
     types
    -0.06
    霊
    -0.06
     norms
    -0.06
     oranı
    -0.06
     Proc
    -0.06
     assurance
    -0.06
    POSITIVE LOGITS
    _listener
    0.07
     PKK
    0.06
     şans
    0.06
     si
    0.06
    eygamber
    0.06
    ـــ
    0.06
    /false
    0.06
     폭
    0.06
     sucht
    0.06
    �다
    0.06
    Act Density 0.009%

    No Known Activations