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

    Neuronpedia

    INDEX
    Explanations

    Negative connotations or fairness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    era
    -1.13
     offensive
    -0.98
     harsh
    -0.85
    ERA
    -0.85
     fair
    -0.83
     Offensive
    -0.81
    Offensive
    -0.79
    e
    -0.75
    offensive
    -0.73
     offensi
    -0.65
    POSITIVE LOGITS
     nakalista
    0.88
     समीक्षाओं
    0.75
    bootstrapcdn
    0.71
    providedIn
    0.66
    ActionCreators
    0.66
     CreateTagHelper
    0.65
     nonatomic
    0.65
    eseorang
    0.65
    Tracce
    0.65
    tvguidetime
    0.64
    Act Density 0.900%

    No Known Activations