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

    Neuronpedia

    INDEX
    Explanations

    side effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Гра
    0.72
    トロ
    0.68
    ढ़ा
    0.68
    慷
    0.67
     Interpol
    0.65
    แป
    0.65
    GRAPH
    0.64
    Kap
    0.64
     کپ
    0.63
    aryana
    0.63
    POSITIVE LOGITS
     stencil
    0.61
     mif
    0.60
    ēja
    0.59
    acje
    0.59
    েক
    0.57
     bands
    0.56
     prescribe
    0.55
    ac
    0.55
     bittern
    0.54
    estris
    0.54
    Act Density 0.231%

    No Known Activations