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

    Neuronpedia

    INDEX
    Explanations

    max-width and height

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     march
    0.38
     personal
    0.36
    orta
    0.36
     squat
    0.35
     shopper
    0.35
     शुक्
    0.34
     личности
    0.34
     буль
    0.34
     mult
    0.34
     பாது
    0.34
    POSITIVE LOGITS
    菌
    0.39
     Pics
    0.39
    %。
    0.38
     Perg
    0.38
     Actin
    0.37
    brecht
    0.37
     karm
    0.37
     Helic
    0.36
    Picklist
    0.36
     reste
    0.36
    Act Density 0.001%

    No Known Activations