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

    Neuronpedia

    INDEX
    Explanations

    spac

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     refuge
    -0.07
    gratis
    -0.07
    elps
    -0.07
    ropoda
    -0.07
     �
    -0.07
    \Template
    -0.07
     eskorte
    -0.06
    ndern
    -0.06
    gii
    -0.06
    рім
    -0.06
    POSITIVE LOGITS
     spac
    0.10
    /[
    0.07
     exposing
    0.06
    Scores
    0.06
    :])↵
    0.06
     Tomas
    0.06
     heed
    0.06
     wig
    0.06
     mem
    0.06
     suppressing
    0.06
    Act Density 0.001%

    No Known Activations