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

    Neuronpedia

    INDEX
    Explanations

    business proposals and opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pricey
    0.42
    हीं
    0.42
    Learning
    0.41
    pple
    0.41
    checks
    0.40
    boosting
    0.40
    影响
    0.39
     fréquentes
    0.39
    pples
    0.38
    توى
    0.38
    POSITIVE LOGITS
     pursuant
    0.86
     Pursuant
    0.69
     commencing
    0.68
     heretofore
    0.68
     commences
    0.68
     Notwithstanding
    0.66
     forthwith
    0.66
     commencement
    0.65
     contemplates
    0.63
     commenced
    0.63
    Act Density 0.015%

    No Known Activations