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

    Neuronpedia

    INDEX
    Explanations

    can perform middle toes bare bulb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilise
    0.52
     grassland
    0.48
     possibles
    0.47
     grasslands
    0.44
     atlet
    0.44
     utilis
    0.44
     utilises
    0.43
     utilisent
    0.43
     avert
    0.43
     possíveis
    0.43
    POSITIVE LOGITS
     සැ
    0.48
    Ợ
    0.40
    SPAN
    0.40
    WIT
    0.39
    Solve
    0.39
    utional
    0.38
     კომ
    0.38
    neet
    0.38
    UM
    0.38
     Vary
    0.38
    Act Density 0.000%

    No Known Activations