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

    Neuronpedia

    INDEX
    Explanations

    pairs, JSON, data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MinIntensity
    0.53
    InfoPlist
    0.51
     enzimas
    0.48
    LFT
    0.47
    RoutingModule
    0.47
     Einstellungen
    0.47
    桻
    0.46
    ându
    0.46
     शिवाय
    0.45
     〢
    0.45
    POSITIVE LOGITS
    t
    0.42
     LAND
    0.42
     water
    0.41
    美好
    0.40
    ре
    0.39
     condition
    0.39
     contend
    0.39
    тного
    0.39
    sinh
    0.39
     garnered
    0.38
    Act Density 0.000%

    No Known Activations