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

    Neuronpedia

    INDEX
    Explanations

    group theory or therapy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    global
    0.39
    盒
    0.39
    Bart
    0.38
    Parks
    0.38
    erweise
    0.38
    Ghosts
    0.38
     Crews
    0.37
    between
    0.37
     ലോക
    0.36
    Strip
    0.35
    POSITIVE LOGITS
    成員
    0.63
     disbanded
    0.61
     members
    0.58
     halinde
    0.57
     subgroups
    0.56
     dynamics
    0.55
    mitglied
    0.55
     Dynamics
    0.54
     subgroup
    0.53
     cohesion
    0.53
    Act Density 0.027%

    No Known Activations