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

    Neuronpedia

    INDEX
    Explanations

    still life and stillness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meaningful
    0.43
     kode
    0.42
     accruing
    0.42
     raison
    0.42
     aggregated
    0.41
     association
    0.41
     implementations
    0.41
     asociaciones
    0.40
    gged
    0.39
     triggering
    0.39
    POSITIVE LOGITS
    不动
    0.58
    waters
    0.47
    Static
    0.46
     Static
    0.44
     さらに
    0.42
    HIG
    0.41
    ames
    0.40
    그리고
    0.40
     waters
    0.40
    SB
    0.40
    Act Density 0.002%

    No Known Activations