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

    Neuronpedia

    INDEX
    Explanations

    during the, deeper…, Ver-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ক্রোধ
    0.39
     marah
    0.36
     Soils
    0.35
    *((*
    0.35
    婊
    0.35
     Pogba
    0.35
    虢
    0.34
     irritated
    0.34
     offended
    0.33
    ikannya
    0.33
    POSITIVE LOGITS
    UR
    0.40
    MS
    0.40
    ML
    0.39
    UNE
    0.37
    BUS
    0.36
    AUX
    0.36
    LEV
    0.36
    ","/
    0.36
    公正
    0.35
    boldsymbol
    0.35
    Act Density 0.000%

    No Known Activations