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

    Neuronpedia

    INDEX
    Explanations

    memory addressing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gobierno
    -0.07
     defects
    -0.07
    ++;↵
    -0.07
     ISPs
    -0.07
     TMZ
    -0.06
    locator
    -0.06
    yang
    -0.06
    —I
    -0.06
    ?",↵
    -0.06
     Fu
    -0.06
    POSITIVE LOGITS
    cents
    0.07
     زندگی
    0.07
    -existent
    0.06
    ;amp
    0.06
    ptron
    0.06
    cent
    0.06
     νεφοκάλυψης
    0.06
    مي
    0.06
     PdfPCell
    0.06
     pname
    0.06
    Act Density 0.014%

    No Known Activations