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

    Neuronpedia

    INDEX
    Explanations

    Optimization algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gameState
    -0.07
    _choose
    -0.07
    -0.07
    491
    -0.07
     snake
    -0.07
    Roger
    -0.07
    expectException
    -0.07
    Jud
    -0.07
     Salad
    -0.07
    Stephen
    -0.06
    POSITIVE LOGITS
    ій
    0.06
     Bitcoin
    0.06
     filming
    0.06
     tái
    0.06
    ْس
    0.06
    incipal
    0.06
     عقد
    0.06
     ${({
    0.06
    banks
    0.05
    cess
    0.05
    Act Density 0.037%

    No Known Activations