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

    Neuronpedia

    INDEX
    Explanations

    intensifying context following "extreme"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    1.13
    र
    1.07
    er
    1.06
    ofinstagram
    1.03
    א
    1.00
    পোষ
    0.96
    ל
    0.95
     nifty
    0.94
    ה
    0.93
    ا
    0.92
    POSITIVE LOGITS
     важно
    1.19
    нием
    1.18
     scrutiny
    1.14
    ยาว
    1.09
     variability
    1.04
    𝒔
    1.03
     tärke
    1.01
     makeover
    1.01
    𝒕
    1.01
    सरत
    1.00
    Act Density 0.088%

    No Known Activations