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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Refs
    -0.06
    た
    -0.06
     tenant
    -0.06
     Rit
    -0.06
    yd
    -0.06
    .Return
    -0.06
    gium
    -0.06
    protocols
    -0.06
    nal
    -0.06
    udic
    -0.06
    POSITIVE LOGITS
    ยาว
    0.06
    ріп
    0.06
     artistic
    0.06
    _BASE
    0.06
    stasy
    0.06
    لاف
    0.06
     جوان
    0.06
    ักษณ
    0.06
    ATTLE
    0.06
     Representatives
    0.06
    Act Density 0.001%

    No Known Activations