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

    Neuronpedia

    INDEX
    Explanations

    grating sounds

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Proceed
    0.39
    Proceed
    0.38
    逵
    0.38
    মর
    0.36
    צה
    0.35
    =""><
    0.35
     المطل
    0.34
     meditating
    0.34
    Analog
    0.34
    ጠን
    0.34
    POSITIVE LOGITS
     cor
    0.46
     ch
    0.45
     Hamid
    0.43
     chit
    0.42
     superiori
    0.41
     superior
    0.40
     twist
    0.39
     squ
    0.37
     sque
    0.37
     superiore
    0.37
    Act Density 0.057%

    No Known Activations