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

    Neuronpedia

    INDEX
    Explanations

    Code/Documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isAdmin
    -0.07
    IER
    -0.07
    safe
    -0.06
    (hidden
    -0.06
     hatch
    -0.06
     Josh
    -0.06
    scheduler
    -0.06
    为了
    -0.06
    @brief
    -0.06
    En
    -0.06
    POSITIVE LOGITS
     hk
    0.07
     scalp
    0.06
     helium
    0.06
     ASM
    0.06
     패
    0.06
     fragmentation
    0.06
     clot
    0.06
     Кроме
    0.06
     Kazakhstan
    0.06
     Localization
    0.06
    Act Density 0.161%

    No Known Activations