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

    Neuronpedia

    INDEX
    Explanations

    Expressing opinions/thoughts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ſelves
    -0.80
     raiſ
    -0.76
     $_"
    -0.76
     faſt
    -0.74
     EconPapers
    -0.73
     auffi
    -0.72
     purpoſe
    -0.72
     Anſ
    -0.72
     Efq
    -0.72
     cauſe
    -0.71
    POSITIVE LOGITS
     I
    1.25
     i
    0.73
    ,
    0.69
     
    0.63
    :
    0.63
    .
    0.57
    I
    0.57
     it
    0.56
    ScopeManager
    0.54
    ...
    0.53
    Act Density 0.912%

    No Known Activations