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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    properties
    -0.07
    (Column
    -0.07
    озд
    -0.06
    (size
    -0.06
     nod
    -0.06
     สำหร
    -0.06
     mature
    -0.06
    //*[@
    -0.06
    categories
    -0.06
     highways
    -0.06
    POSITIVE LOGITS
    qq
    0.06
     Hawaiian
    0.06
     selfie
    0.06
    erral
    0.06
    賣
    0.06
    URAL
    0.06
    .HE
    0.06
     môi
    0.06
     ніж
    0.06
     alot
    0.06
    Act Density 0.074%

    No Known Activations