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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    early
    -0.07
    Count
    -0.07
    hello
    -0.06
    elfast
    -0.06
    .tt
    -0.06
    udget
    -0.06
    itest
    -0.06
    _Two
    -0.06
     Since
    -0.06
    ièrement
    -0.06
    POSITIVE LOGITS
    PCM
    0.07
    954
    0.06
     aquel
    0.06
     COLORS
    0.06
    Outlined
    0.06
    Link
    0.06
    -aos
    0.06
     behind
    0.06
     inviting
    0.06
    งใน
    0.06
    Act Density 0.006%

    No Known Activations