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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atri
    -0.07
    .high
    -0.07
     '#
    -0.07
     nab
    -0.06
     coerce
    -0.06
     Ad
    -0.06
    ازم
    -0.06
    NI
    -0.06
    .Spec
    -0.06
     cleanse
    -0.06
    POSITIVE LOGITS
     informs
    0.06
     MOUSE
    0.06
     없
    0.06
    pagen
    0.06
     Dynamic
    0.06
     spiders
    0.06
    _balance
    0.06
    Manual
    0.06
    (Result
    0.06
    (Parameter
    0.06
    Act Density 0.015%

    No Known Activations