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

    Neuronpedia

    INDEX
    Explanations

    Orthodox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Runnable
    -0.07
    阵
    -0.07
     clim
    -0.07
     minib
    -0.07
     dbg
    -0.07
     Reward
    -0.07
    띈
    -0.07
    驭
    -0.07
     Candid
    -0.07
    erk
    -0.06
    POSITIVE LOGITS
    pliant
    0.08
    .Photo
    0.08
     pelos
    0.07
     oak
    0.07
     daughters
    0.07
    transforms
    0.07
     oxide
    0.07
    有限公司
    0.07
    ophone
    0.07
    ходить
    0.07
    Act Density 0.001%

    No Known Activations