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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Promise
    -0.07
    (strings
    -0.07
    <Course
    -0.07
    _regular
    -0.07
    .terminate
    -0.06
     hadde
    -0.06
     Ground
    -0.06
    .parseLong
    -0.06
     testament
    -0.06
    750
    -0.06
    POSITIVE LOGITS
    Metric
    0.07
    (saved
    0.06
     totalmente
    0.06
    مارات
    0.06
    ủi
    0.06
     Rowling
    0.06
    0.06
     posible
    0.06
    vala
    0.06
    Chinese
    0.06
    Act Density 0.095%

    No Known Activations