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

    Neuronpedia

    INDEX
    Explanations

    General text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    beh
    -0.07
     wallets
    -0.06
    222
    -0.06
    ~/
    -0.06
     pagar
    -0.06
     Meal
    -0.06
     plenty
    -0.06
    MISS
    -0.06
    (PARAM
    -0.06
    /ex
    -0.06
    POSITIVE LOGITS
    ivatel
    0.07
     přist
    0.07
     Crosby
    0.06
     Carn
    0.06
     JADX
    0.06
    zioni
    0.06
     Lamar
    0.06
    AttribPointer
    0.06
     Qin
    0.06
    eventName
    0.06
    Act Density 1.548%

    No Known Activations