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

    Neuronpedia

    INDEX
    Explanations

    when or if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     advocated
    0.46
     hydrophilic
    0.46
     prioritized
    0.46
     hydrological
    0.44
     emphasized
    0.44
     inund
    0.43
     adaptable
    0.43
     hydro
    0.43
     bouncy
    0.43
     effluent
    0.42
    POSITIVE LOGITS
     직접
    0.48
     när
    0.47
    Когда
    0.46
    praw
    0.46
     когда
    0.46
    जब
    0.45
     włas
    0.45
    Lorsque
    0.45
    quando
    0.45
    เมื่อ
    0.44
    Act Density 0.005%

    No Known Activations