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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     говор
    -0.07
    Nama
    -0.06
     Gang
    -0.06
    Thumb
    -0.06
     endl
    -0.06
    "));
    -0.06
    abama
    -0.06
    ुल
    -0.06
     Param
    -0.06
    álu
    -0.06
    POSITIVE LOGITS
    ág
    0.07
    itamin
    0.07
    511
    0.07
    osa
    0.06
     environmental
    0.06
     finances
    0.06
     monitors
    0.06
     ç
    0.06
    _ASCII
    0.06
     ensure
    0.06
    Act Density 0.002%

    No Known Activations