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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    10
    -0.07
    'clock
    -0.07
    prob
    -0.07
    666
    -0.07
    11
    -0.07
    39
    -0.07
    ْل
    -0.07
    /[
    -0.07
    hei
    -0.06
     create
    -0.06
    POSITIVE LOGITS
     Bruno
    0.07
     зав
    0.07
    います
    0.06
     distributes
    0.06
     таблет
    0.06
     automated
    0.06
     U
    0.06
    дап
    0.06
     adı
    0.06
    Outlined
    0.05
    Act Density 0.006%

    No Known Activations