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

    Neuronpedia

    INDEX
    Explanations

    general

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     focussed
    1.28
    Focus
    1.24
     focused
    1.23
    Focused
    1.23
    FOCUS
    1.13
     Focused
    1.11
     focussing
    1.11
     focusing
    1.09
    focused
    1.04
    That
    1.03
    POSITIVE LOGITS
     General
    0.86
     general
    0.77
     GENERAL
    0.77
     room
    0.74
     Allgeme
    0.73
     generales
    0.71
    general
    0.71
     estamos
    0.69
     Room
    0.67
     जागे
    0.67
    Act Density 0.000%

    No Known Activations