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

    Neuronpedia

    INDEX
    Explanations

    anniversaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Woche
    -0.07
    (factor
    -0.06
     düzey
    -0.06
     최대
    -0.06
    -taking
    -0.06
     подроб
    -0.06
    Jets
    -0.06
     masturbating
    -0.06
     陈
    -0.06
     RESP
    -0.06
    POSITIVE LOGITS
    <Pair
    0.07
    熊
    0.06
    ('{{
    0.06
    �
    0.06
     Lincoln
    0.06
    Boost
    0.06
    (Environment
    0.06
    짝
    0.06
    ,value
    0.06
    NavigationView
    0.06
    Act Density 0.026%

    No Known Activations