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

    Neuronpedia

    INDEX
    Explanations

    confirmation and tag questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wyniku
    0.41
    סי
    0.41
    }=\
    0.40
     torchvision
    0.39
     frmt
    0.39
     equilibration
    0.38
     residue
    0.38
    煐
    0.38
     volatiles
    0.38
     quercetin
    0.38
    POSITIVE LOGITS
    вичайно
    0.55
    이죠
    0.51
    ですよね
    0.51
     طبعا
    0.49
     oczywiście
    0.45
     admittedly
    0.45
     appunto
    0.45
     বটে
    0.45
     конечно
    0.44
     เนาะ
    0.44
    Act Density 0.092%

    No Known Activations