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

    Neuronpedia

    INDEX
    Explanations

    presentation excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DECLARE
    -0.07
    เอส
    -0.07
    Recipe
    -0.07
     PropelException
    -0.07
     themselves
    -0.07
    _dp
    -0.06
    ስ
    -0.06
     Melbourne
    -0.06
     PH
    -0.06
    尔斯
    -0.06
    POSITIVE LOGITS
    🍽
    0.07
     '%$
    0.06
    抓紧
    0.06
     języ
    0.06
    ยอม
    0.06
    .market
    0.06
    TintColor
    0.06
    _adapter
    0.06
    葆
    0.06
    但是对于
    0.06
    Act Density 0.070%

    No Known Activations