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

    Neuronpedia

    INDEX
    Explanations

    parchment or silicone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     സ്ത്ര
    0.43
     fotografía
    0.40
    AxisSize
    0.40
    सवाल
    0.39
     kuru
    0.39
    لاع
    0.38
    ட
    0.38
     너
    0.38
    0.38
    ኾ
    0.37
    POSITIVE LOGITS
     parchment
    0.50
    cal
    0.48
     directed
    0.47
     targeted
    0.47
     gene
    0.46
    default
    0.44
     disruptive
    0.44
     visibility
    0.44
     draft
    0.43
     alten
    0.42
    Act Density 0.002%

    No Known Activations