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

    Neuronpedia

    INDEX
    Explanations

    subtraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mek
    -0.07
    _intensity
    -0.07
    сон
    -0.07
     UnityEngine
    -0.07
    Rub
    -0.07
     Goat
    -0.06
     diesen
    -0.06
    ็ก
    -0.06
    irt
    -0.06
    Te
    -0.06
    POSITIVE LOGITS
    DW
    0.07
    yst
    0.06
    advance
    0.06
     ;-
    0.06
    (expr
    0.06
    나요
    0.06
    hell
    0.06
     """
↵
↵
    0.06
    -den
    0.06
     STOCK
    0.06
    Act Density 0.001%

    No Known Activations