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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >n
    -0.06
     Fou
    -0.06
    /co
    -0.06
     derivation
    -0.06
    zan
    -0.06
    /container
    -0.06
     AIDS
    -0.06
     silicone
    -0.05
     Pitch
    -0.05
     Coordinates
    -0.05
    POSITIVE LOGITS
    sdk
    0.07
     مج
    0.07
     фер
    0.07
     currentPlayer
    0.07
     painfully
    0.07
     heartfelt
    0.06
    用
    0.06
    Skin
    0.06
    백
    0.06
     juegos
    0.06
    Act Density 0.001%

    No Known Activations