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

    Neuronpedia

    INDEX
    Explanations

    Motor Group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patrols
    0.41
     sneaking
    0.38
     reve
    0.37
     gui
    0.35
     sneak
    0.35
     書い
    0.35
     villains
    0.34
    ंछ
    0.34
     parametr
    0.34
    unpublished
    0.34
    POSITIVE LOGITS
    多分
    0.30
    Normal
    0.30
    ificar
    0.30
    jquery
    0.29
    Эти
    0.29
     تقس
    0.29
    these
    0.29
    edizione
    0.28
    Aggregate
    0.28
    रूप
    0.28
    Act Density 0.001%

    No Known Activations