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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    طار
    -0.06
    腹
    -0.06
    	resource
    -0.06
    icí
    -0.06
    وية
    -0.06
    \Collection
    -0.06
    ằ
    -0.06
    uegos
    -0.06
     Ne
    -0.06
    PropertyValue
    -0.06
    POSITIVE LOGITS
    /r
    0.07
     περ
    0.07
    OLTIP
    0.07
     Lớp
    0.06
     oslo
    0.06
     lubric
    0.06
     strand
    0.06
    ub
    0.06
    eck
    0.06
     большой
    0.06
    Act Density 0.041%

    No Known Activations