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

    Neuronpedia

    INDEX
    Explanations

    action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BECAUSE
    0.55
     ហើយ
    0.53
     AND
    0.47
     وما
    0.46
     و
    0.45
     etc
    0.45
     یا
    0.44
     เพราะ
    0.43
     أو
    0.43
    Iv
    0.43
    POSITIVE LOGITS
     belated
    0.54
     longstanding
    0.49
     lucrative
    0.48
     cinquième
    0.46
     geralmente
    0.46
    йте
    0.46
     voidaan
    0.46
     наиболее
    0.44
    जन्य
    0.44
     преимуще
    0.44
    Act Density 0.000%

    No Known Activations