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

    Neuronpedia

    INDEX
    Explanations

    the words "uncertainty" and "nephews"

    oai_token-act-pair · gemini-2.0-flash

    family/uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ['./
    -0.57
     allons
    -0.57
     furent
    -0.57
     alatt
    -0.57
     ‘
    -0.57
     the
    -0.56
    выше
    -0.55
     didalam
    -0.54
     valamint
    -0.53
     diatas
    -0.52
    POSITIVE LOGITS
     XNUMX
    1.14
     שוליים
    1.08
    ConstraintMaker
    1.07
     iſt
    1.05
     ―――――
    1.02
    enumi
    1.00
    migrationBuilder
    0.98
    +#+#
    0.96
    NewUrlParser
    0.95
     myſelf
    0.95
    Act Density 1.542%

    No Known Activations