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

    Neuronpedia

    INDEX
    Explanations

    OF

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raud
    -0.07
    凉
    -0.06
    로는
    -0.06
    wear
    -0.06
     brand
    -0.06
     loan
    -0.06
     herbs
    -0.06
     broth
    -0.06
    an
    -0.06
     raw
    -0.06
    POSITIVE LOGITS
    imag
    0.07
    xFC
    0.07
    のように
    0.06
     showError
    0.06
     siyaset
    0.06
     сахар
    0.06
    TickCount
    0.06
    ㅋㅋㅋㅋ
    0.06
    	NullCheck
    0.06
     aseg
    0.06
    Act Density 0.004%

    No Known Activations