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

    Neuronpedia

    INDEX
    Explanations

    words that indicate a turning point or a significant event

    oai_token-act-pair · gemini-2.0-flash

    High point

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     محفوظة
    -0.73
     CreateTagHelper
    -0.68
    ReusableCell
    -0.65
    UrlResolution
    -0.60
     ReactDOM
    -0.60
     kasarigan
    -0.60
    Autoritní
    -0.57
    PerformLayout
    -0.57
     teg
    -0.56
    исленность
    -0.56
    POSITIVE LOGITS
     climax
    0.84
     peak
    0.84
     tipping
    0.83
     watershed
    0.76
     turning
    0.75
    peak
    0.74
     Peak
    0.73
    Peak
    0.72
     inflection
    0.71
     PEAK
    0.71
    Act Density 1.703%

    No Known Activations