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

    Neuronpedia

    INDEX
    Explanations

    historical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ev
    0.48
     Ult
    0.47
     nødv
    0.45
    isocyanate
    0.44
    雖
    0.44
    豸
    0.44
     आवश्यक
    0.43
     Commodities
    0.43
     टीकाकरण
    0.42
     बैलेंस
    0.42
    POSITIVE LOGITS
    ’
    0.55
    x
    0.48
    work
    0.46
     wir
    0.46
    都合
    0.45
    movement
    0.44
    o
    0.44
     movement
    0.43
     desires
    0.43
    minor
    0.42
    Act Density 0.000%

    No Known Activations