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

    Neuronpedia

    INDEX
    Explanations

    ranging from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ક્રિય
    0.48
     plais
    0.44
     ambition
    0.41
    प्पू
    0.41
     방법을
    0.41
     doings
    0.40
    ജീവ
    0.40
    他們
    0.40
     idealism
    0.39
     Them
    0.39
    POSITIVE LOGITS
    ะ
    0.47
     of
    0.45
     decir
    0.43
     olarak
    0.42
     universally
    0.41
    ının
    0.40
     marchio
    0.40
     கூறப்படுகிறது
    0.40
     tertinggi
    0.40
    ر
    0.40
    Act Density 0.009%

    No Known Activations