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

    Neuronpedia

    INDEX
    Explanations

    duration in hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erns
    0.97
    pine
    0.83
     res
    0.76
     cents
    0.72
     parallel
    0.72
    <0xA8>
    0.72
    年から
    0.72
     আনুশকা
    0.71
     values
    0.71
     meg
    0.71
    POSITIVE LOGITS
     Hydrochloride
    0.75
     Equitable
    0.75
     Tight
    0.74
     Matcha
    0.73
     Deep
    0.71
     abundante
    0.71
     વિક
    0.70
     Mindfulness
    0.69
     Iya
    0.68
     Overflow
    0.68
    Act Density 0.469%

    No Known Activations