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

    Neuronpedia

    INDEX
    Explanations

    Brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -1.68
     itſelf
    -0.95
    ième
    -0.70
     Jefus
    -0.70
     faſt
    -0.68
    seamnă
    -0.65
     myſelf
    -0.64
     ſy
    -0.63
     raiſ
    -0.63
     pleaſure
    -0.63
    POSITIVE LOGITS
     >=",
    0.61
    LookAnd
    0.60
     pu
    0.56
    '
    0.56
    ".
    0.55
    HasAnnotation
    0.55
    \{\\
    0.53
     Chwiliwch
    0.53
     nakalista
    0.53
    mudi
    0.52
    Act Density 0.071%

    No Known Activations