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

    Neuronpedia

    INDEX
    Explanations

    disagreement or opposition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *pow
    -0.06
    ataloader
    -0.06
    (z
    -0.06
    Ai
    -0.06
     Jackson
    -0.06
     faz
    -0.06
     fontStyle
    -0.06
     abrir
    -0.06
    Translated
    -0.06
    ,v
    -0.06
    POSITIVE LOGITS
     SRC
    0.07
    _allocate
    0.06
    illas
    0.06
     wiel
    0.06
    νοι
    0.06
    ziej
    0.06
     RCA
    0.06
    iyim
    0.06
     категор
    0.06
    روت
    0.06
    Act Density 0.045%

    No Known Activations