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

    Neuronpedia

    INDEX
    Explanations

    academic/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.56
    mainAxisSize
    -0.50
     >>
    -0.50
     —
    -0.48
     referenties
    -0.47
    ↵↵
    -0.47
    ...
    -0.46
     Reverso
    -0.46
    bootstrapcdn
    -0.43
    .
    -0.43
    POSITIVE LOGITS
     raiſ
    0.80
     itſelf
    0.74
     faſt
    0.74
     ſta
    0.73
     uſed
    0.72
     ſmall
    0.71
    '}>
    0.66
     Diſ
    0.66
    ')")
    0.65
    ſelves
    0.65
    Act Density 0.003%

    No Known Activations