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

    Neuronpedia

    INDEX
    Explanations

    humans, ethane, graphics, expand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inciting
    0.47
     O
    0.47
    ↵
    0.44
     R
    0.43
     Newly
    0.42
     tang
    0.42
    -
    0.41
     Sein
    0.41
    mang
    0.41
    кто
    0.40
    POSITIVE LOGITS
    Aux
    0.52
    MktCap
    0.52
    র্কের
    0.51
    FY
    0.50
     astrological
    0.49
    DepartTime
    0.49
    Departamento
    0.48
    AsyncKeyState
    0.48
    Aile
    0.47
    újt
    0.47
    Act Density 0.002%

    No Known Activations