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

    Neuronpedia

    INDEX
    Explanations

    comparison and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fiberglass
    0.57
     stitches
    0.48
     cowboy
    0.48
     skin
    0.46
     mig
    0.45
     crossbow
    0.45
     bristles
    0.44
     sleeves
    0.43
     samurai
    0.43
     кори
    0.43
    POSITIVE LOGITS
    ürich
    0.47
     రహ
    0.45
    䂘
    0.45
    ్ర
    0.43
    统治
    0.43
    )}=
    0.42
    opedia
    0.42
     digesting
    0.41
    哫
    0.41
    itaire
    0.41
    Act Density 0.002%

    No Known Activations