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

    Neuronpedia

    INDEX
    Explanations

    helm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PR
    -0.09
    Print
    -0.08
    inea
    -0.08
     pog
    -0.07
     April
    -0.07
     Midnight
    -0.07
    "Just
    -0.07
    tered
    -0.07
    PTH
    -0.07
    突
    -0.07
    POSITIVE LOGITS
    頂き
    0.07
     firmly
    0.07
    发展机遇
    0.07
    骗局
    0.07
    筀
    0.07
     Elm
    0.07
    行列
    0.06
     bordered
    0.06
     publishers
    0.06
     queried
    0.06
    Act Density 0.002%

    No Known Activations