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

    Neuronpedia

    INDEX
    Explanations

    contends

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izophren
    -0.09
     of
    -0.07
    南京市
    -0.07
    Arc
    -0.07
    Hex
    -0.07
    Sw
    -0.07
    ascar
    -0.07
    acial
    -0.07
    ENU
    -0.07
    顾客
    -0.07
    POSITIVE LOGITS
    ￨
    0.07
     pud
    0.07
    	prev
    0.06
     …↵↵
    0.06
    .’”↵↵
    0.06
    𝒈
    0.06
     יעל
    0.06
     beet
    0.06
     tires
    0.06
     searching
    0.06
    Act Density 0.002%

    No Known Activations