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

    Neuronpedia

    INDEX
    Explanations

    the Regular, the Problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     불구하고
    1.08
     enquiries
    1.03
     engravings
    1.01
    多くの
    0.98
     goles
    0.97
     handsets
    0.96
     animations
    0.95
     assemblages
    0.95
     त्यामुळे
    0.94
     większość
    0.93
    POSITIVE LOGITS
    د
    0.95
    ד
    0.91
    ну
    0.89
    न
    0.84
    ب
    0.82
     nutshell
    0.81
    好
    0.81
    directory
    0.81
    ﺪ
    0.79
    ال
    0.79
    Act Density 0.407%

    No Known Activations