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

    Neuronpedia

    INDEX
    Explanations

    application or product details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.50
    0.45
     unspo
    0.43
     b
    0.43
     \'
    0.42
     the
    0.41
     noch
    0.40
     Overlay
    0.39
    orbidity
    0.39
    oug
    0.39
    POSITIVE LOGITS
    锌
    0.48
     предприя
    0.47
    倞
    0.47
     dépens
    0.46
    ᒥ
    0.46
    Gior
    0.46
    谟
    0.46
     części
    0.46
    Farmers
    0.46
    DEFGHIJKLMNOP
    0.46
    Act Density 0.000%

    No Known Activations