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

    Neuronpedia

    INDEX
    Explanations

    Ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Notre
    -0.08
    CHEMY
    -0.07
    .Validation
    -0.06
    ir
    -0.06
     wget
    -0.06
    托
    -0.06
     висок
    -0.06
    _GRP
    -0.06
    (Common
    -0.06
     refriger
    -0.06
    POSITIVE LOGITS
    Audio
    0.07
    üny
    0.06
     manera
    0.06
     Litecoin
    0.06
     Abed
    0.06
     racket
    0.06
     apare
    0.06
    UserName
    0.06
    些
    0.06
     stron
    0.06
    Act Density 0.003%

    No Known Activations