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

    Neuronpedia

    INDEX
    Explanations

    duration, annual, time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diputado
    0.41
     అమ్మ
    0.41
     மஞ்ச
    0.40
     pienso
    0.40
    imshow
    0.39
     amarilla
    0.39
    fromParams
    0.39
    meshgrid
    0.38
     quarrel
    0.38
     rojo
    0.38
    POSITIVE LOGITS
     Signature
    0.49
     signatures
    0.45
     sooner
    0.42
     Duration
    0.41
     duration
    0.41
    时间和
    0.40
     Warfare
    0.39
     Sign
    0.39
     namely
    0.39
     durée
    0.39
    Act Density 0.001%

    No Known Activations