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

    Neuronpedia

    INDEX
    Explanations

    .md file extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     động
    0.42
     want
    0.40
     extranj
    0.39
     Avan
    0.39
     Jansen
    0.38
     pristup
    0.38
     Thom
    0.37
     ইস্য
    0.37
    ambito
    0.37
     bụng
    0.37
    POSITIVE LOGITS
    converter
    0.41
    rott
    0.41
    表
    0.41
    pap
    0.40
    ucco
    0.39
    attached
    0.39
    pulsewidth
    0.38
     раствора
    0.38
    říklad
    0.37
     dropper
    0.37
    Act Density 0.000%

    No Known Activations