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

    Neuronpedia

    INDEX
    Explanations

    instances of quantifiers or references to numbers and mathematical expressions

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

    rounding numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ESTA
    -0.35
     Ga
    -0.35
     H
    -0.32
    źć
    -0.32
    志
    -0.31
     bou
    -0.31
     jsPsych
    -0.30
     PM
    -0.30
     GA
    -0.30
     Max
    -0.30
    POSITIVE LOGITS
     Geſch
    0.76
     enfans
    0.71
     boneca
    0.68
     Geſ
    0.68
     capucha
    0.67
     saveiro
    0.67
     miniaturka
    0.63
     huelga
    0.63
     cremallera
    0.63
     fieltro
    0.63
    Act Density 0.096%

    No Known Activations