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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    リン
    -0.07
     это
    -0.07
     Las
    -0.07
     JsonSerializer
    -0.07
     performing
    -0.07
     sung
    -0.07
     Technology
    -0.06
    癿
    -0.06
     çocuğu
    -0.06
     foram
    -0.06
    POSITIVE LOGITS
    .'));↵
    0.07
    晊
    0.07
    (param
    0.06
    _ISS
    0.06
    ƈ
    0.06
     rak
    0.06
    PLAN
    0.06
    防
    0.06
    Clar
    0.06
    _Game
    0.06
    Act Density 0.010%

    No Known Activations