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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?????
    -0.07
     Tep
    -0.07
     TEN
    -0.06
    :disable
    -0.06
     Spar
    -0.06
     kter
    -0.06
     disemb
    -0.06
     meats
    -0.06
     nep
    -0.06
     handmade
    -0.06
    POSITIVE LOGITS
    ?“
    0.07
    _attrib
    0.06
    oneksi
    0.06
    薩
    0.06
    耗
    0.06
    faculty
    0.06
     ey
    0.06
     toughness
    0.06
     każ
    0.06
    Axis
    0.06
    Act Density 0.001%

    No Known Activations