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

    Neuronpedia

    INDEX
    Explanations

    mapping terms to following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ကြာ
    0.37
    කාශ
    0.36
    検
    0.36
     அடு
    0.35
     뜻
    0.34
     Holistic
    0.34
     scanf
    0.34
     abgerufen
    0.34
     nhằm
    0.34
     compét
    0.34
    POSITIVE LOGITS
     एकमात्र
    0.44
     sou
    0.43
     അദ്ദേഹ
    0.43
     same
    0.41
    同样的
    0.40
     queen
    0.40
     lords
    0.39
     still
    0.39
    相同的
    0.38
     sør
    0.38
    Act Density 0.000%

    No Known Activations