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

    Neuronpedia

    INDEX
    Explanations

    measurable standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shapes
    0.43
     Shapes
    0.43
     lineups
    0.40
     внутріш
    0.40
     आंकड़े
    0.39
     shape
    0.38
    ışt
    0.38
     शॉर्ट
    0.38
    ESC
    0.38
     quickly
    0.38
    POSITIVE LOGITS
     LAV
    0.39
     Tatha
    0.38
    MessageNow
    0.38
     Lebensmittel
    0.37
     Msg
    0.37
     Mani
    0.37
     Bhagav
    0.36
     Nd
    0.36
    udian
    0.36
    法施行令
    0.35
    Act Density 0.002%

    No Known Activations