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

    Neuronpedia

    INDEX
    Explanations

    generating essays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাচ্চা
    0.42
    我們會
    0.42
     fruity
    0.41
     دود
    0.40
     storyline
    0.40
     ihop
    0.39
     ଏ
    0.39
     duet
    0.39
     JULY
    0.39
     nifty
    0.39
    POSITIVE LOGITS
     essay
    0.44
     Essays
    0.42
     essays
    0.41
    _{-
    0.41
     eagerly
    0.40
    Nicholas
    0.38
    Conversely
    0.38
     Essay
    0.37
     scarcely
    0.36
    essay
    0.36
    Act Density 0.003%

    No Known Activations