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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Js
    -0.06
    kyt
    -0.06
     jednodu
    -0.06
    ुकस
    -0.06
    सल
    -0.06
    foundland
    -0.06
    球
    -0.06
     manga
    -0.06
     nur
    -0.06
     buffs
    -0.06
    POSITIVE LOGITS
    品牌
    0.07
    -corner
    0.06
     권
    0.06
     disponibles
    0.06
     μέχρι
    0.06
    ć
    0.06
     tend
    0.06
    affe
    0.06
    мещ
    0.06
    .+
    0.06
    Act Density 0.003%

    No Known Activations