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

    Neuronpedia

    INDEX
    Explanations

    abbreviations related to modeling assumptions in mathematical or statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    [SMR] discussions or probability questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Keim
    -0.66
     Schie
    -0.64
     «
    -0.63
     Schmitz
    -0.61
     Adamson
    -0.60
     Gaines
    -0.60
    ური
    -0.59
     Spence
    -0.58
     Nieto
    -0.58
     Quig
    -0.57
    POSITIVE LOGITS
    r
    0.72
    rr
    0.69
    getR
    0.67
    rrrr
    0.66
    rdr
    0.64
    rrr
    0.63
    zr
    0.60
    erir
    0.60
    ror
    0.59
    rrrrrr
    0.59
    Act Density 0.341%

    No Known Activations