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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and terms related to statistical estimators

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

    latex math roman font

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.64
    ↵↵
    -0.48
    ↵↵↵
    -0.47
    ab
    -0.45
    etzal
    -0.44
    aw
    -0.43
    ap
    -0.41
     Sewell
    -0.41
     EXCEPT
    -0.41
    }=\{
    -0.41
    POSITIVE LOGITS
    zelfde
    0.67
     zijne
    0.61
    mathrm
    0.58
     silêncio
    0.56
    bibfnamefont
    0.54
     dezelve
    0.54
     mathvariant
    0.54
    migrationBuilder
    0.53
     newOwner
    0.52
     zoude
    0.51
    Act Density 0.001%

    No Known Activations