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

    Neuronpedia

    INDEX
    Explanations

    as a followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.86
     जानवरों
    0.86
    ку
    0.82
     ინფორმა
    0.81
    created
    0.81
    transferases
    0.80
    Alla
    0.80
    kuat
    0.80
    got
    0.79
     as
    0.76
    POSITIVE LOGITS
     součást
    1.09
     prelude
    0.98
     standalone
    0.97
     means
    0.97
     будто
    0.95
     geheel
    0.91
     opposed
    0.91
     backdrop
    0.90
     separate
    0.90
     though
    0.89
    Act Density 0.070%

    No Known Activations