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

    Neuronpedia

    INDEX
    Explanations

    attitude towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     errands
    1.85
     Foam
    1.80
     Ties
    1.77
    stays
    1.73
     havoc
    1.70
     Warhammer
    1.62
     ghe
    1.59
    }$)
    1.59
     इसलिये
    1.59
    ﻱ
    1.59
    POSITIVE LOGITS
    ت
    2.30
    ير
    2.16
    व
    2.11
    ی
    2.09
    나
    2.08
    ה
    1.99
    tter
    1.95
    ب
    1.93
    ット
    1.91
    да
    1.88
    Act Density 0.011%

    No Known Activations