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

    Neuronpedia

    INDEX
    Explanations

    introducing research statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     banners
    0.44
    据说
    0.39
     rubbish
    0.38
     yelling
    0.38
     decirle
    0.38
     невероят
    0.38
     отмечает
    0.38
     нередко
    0.37
     tránsito
    0.37
     suele
    0.36
    POSITIVE LOGITS
     empirically
    0.75
     experimentally
    0.74
     investigated
    0.70
     empirical
    0.68
     quantitatively
    0.64
     extensively
    0.63
     investigate
    0.62
     computationally
    0.57
     survey
    0.56
     evaluated
    0.56
    Act Density 0.018%

    No Known Activations