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

    Neuronpedia

    INDEX
    Explanations

    dialogue transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     naval
    -0.08
    ptic
    -0.07
    Total
    -0.07
    ु
    -0.06
     Mount
    -0.06
    erring
    -0.06
    Mount
    -0.06
    Ju
    -0.06
     rugged
    -0.06
    etas
    -0.06
    POSITIVE LOGITS
    나요
    0.06
    !I
    0.06
     ›
    0.06
    анії
    0.06
    Als
    0.06
    _WEEK
    0.06
     Reasons
    0.06
    ToArray
    0.06
    .img
    0.06
     tidy
    0.06
    Act Density 0.171%

    No Known Activations