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

    Neuronpedia

    INDEX
    Explanations

    Bootstrap code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .communication
    -0.07
    fusion
    -0.07
    ुरस
    -0.07
    Charts
    -0.07
     declarations
    -0.07
     foods
    -0.07
    상을
    -0.06
    ellung
    -0.06
    計
    -0.06
    JsonObject
    -0.06
    POSITIVE LOGITS
    orough
    0.06
    ıldı
    0.06
     Chemistry
    0.06
     lety
    0.06
    _MAPPING
    0.06
    swagen
    0.05
    ाजन
    0.05
    éc
    0.05
     mundane
    0.05
    好的
    0.05
    Act Density 0.007%

    No Known Activations