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

    Neuronpedia

    INDEX
    Explanations

    life and the body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    able
    0.65
    ou
    0.65
    larla
    0.65
    v
    0.63
    Alternatively
    0.61
    ies
    0.61
    le
    0.59
    or
    0.59
    }$,
    0.59
    ьте
    0.59
    POSITIVE LOGITS
    珵
    0.72
    যাপন
    0.71
    䄳
    0.70
    មា
    0.68
     człowieka
    0.68
     turmoil
    0.67
     presenceData
    0.66
    㖣
    0.66
    撼
    0.66
    гатьох
    0.65
    Act Density 2.699%

    No Known Activations