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

    Neuronpedia

    INDEX
    Explanations

    left supplies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     параметр
    0.40
    مي
    0.40
     OSHA
    0.39
    èles
    0.39
     Amsterdam
    0.38
     индекс
    0.38
     Sal
    0.38
     ალ
    0.37
     அனைத்து
    0.37
    Შ
    0.37
    POSITIVE LOGITS
     telemetry
    0.44
     arabic
    0.42
     acepta
    0.42
     seb
    0.42
     diterima
    0.42
     rear
    0.41
     deep
    0.40
     clover
    0.40
     catalytic
    0.40
     hydride
    0.40
    Act Density 0.000%

    No Known Activations