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

    Neuronpedia

    INDEX
    Explanations

    Programming exception/error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caves
    -0.08
    asis
    -0.07
    agas
    -0.06
    (named
    -0.06
    زن
    -0.06
    Allocate
    -0.06
    hints
    -0.06
     ngon
    -0.06
     sàng
    -0.06
    ewhere
    -0.06
    POSITIVE LOGITS
    meal
    0.07
    ‌م
    0.07
    狂
    0.06
     مواط
    0.06
    .Move
    0.06
    적인
    0.06
    StateMachine
    0.06
     terribly
    0.06
    541
    0.06
    Local
    0.06
    Act Density 0.005%

    No Known Activations