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

    Neuronpedia

    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ема
    -0.06
     Overse
    -0.06
    _leave
    -0.06
    Num
    -0.06
     folding
    -0.06
    Material
    -0.06
    "N
    -0.06
    -cent
    -0.06
    ド
    -0.06
    "If
    -0.06
    POSITIVE LOGITS
     món
    0.07
    .when
    0.07
     suk
    0.06
     clearInterval
    0.06
     مک
    0.06
    	duration
    0.06
    abajo
    0.06
     étaient
    0.06
     traged
    0.06
     dele
    0.06
    Act Density 0.009%

    No Known Activations