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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ersed
    -0.06
    ेल
    -0.06
    ुग
    -0.06
    Declare
    -0.06
     posture
    -0.06
    刚
    -0.06
     piece
    -0.06
    495
    -0.05
    blade
    -0.05
    계
    -0.05
    POSITIVE LOGITS
    ***
    0.09
     CLICK
    0.07
     alım
    0.07
     стало
    0.06
     erk
    0.06
    核心
    0.06
     J
    0.06
     outsourcing
    0.06
    /by
    0.06
    discover
    0.06
    Act Density 0.127%

    No Known Activations