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

    Neuronpedia

    INDEX
    Explanations

    ranking and popularity qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     than
    1.02
     niż
    0.98
     Than
    0.93
     än
    0.85
    than
    0.80
     prone
    0.77
     elsewhere
    0.75
    更加
    0.73
    }}{|
    0.71
     "|
    0.71
    POSITIVE LOGITS
     talked
    1.31
     cited
    1.24
     hated
    1.10
    watched
    1.09
     quoted
    1.08
     complained
    1.05
     photographed
    1.05
     searched
    1.05
     important
    1.03
     discussed
    1.01
    Act Density 0.177%

    No Known Activations