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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fo
    -0.06
     cur
    -0.06
     stren
    -0.06
    ')],↵
    -0.06
     traff
    -0.06
    Stack
    -0.06
    ids
    -0.06
    armor
    -0.06
     系
    -0.06
    .schedule
    -0.06
    POSITIVE LOGITS
     prayed
    0.07
    .pen
    0.07
    ollipop
    0.06
    nutí
    0.06
     الشركة
    0.06
    DTV
    0.06
    KANJI
    0.06
    	input
    0.06
     oğlu
    0.06
     incididunt
    0.06
    Act Density 0.066%

    No Known Activations