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

    Neuronpedia

    INDEX
    Explanations

    LLC and financial terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finely
    0.45
    ющейся
    0.44
     yardım
    0.42
     água
    0.42
     skú
    0.42
     discreet
    0.41
     subtle
    0.40
     débat
    0.40
     لوی
    0.40
     fountain
    0.40
    POSITIVE LOGITS
    ל
    0.57
    ט
    0.55
    Methyl
    0.53
    น
    0.53
    Metal
    0.52
    כ
    0.51
    न
    0.50
    Mobile
    0.50
    า
    0.49
    ра
    0.47
    Act Density 0.000%

    No Known Activations