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

    Neuronpedia

    INDEX
    Explanations

    composed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Universe
    -0.07
    amin
    -0.06
     مون
    -0.06
     bracelet
    -0.06
    Ban
    -0.06
     NOTHING
    -0.05
     squirrel
    -0.05
    _regularizer
    -0.05
     використовувати
    -0.05
    })",
    -0.05
    POSITIVE LOGITS
    灭
    0.07
    gende
    0.07
     основі
    0.07
     Terr
    0.06
     answering
    0.06
     Uh
    0.06
    -г
    0.06
     국
    0.06
     už
    0.06
    ]=[
    0.06
    Act Density 0.001%

    No Known Activations