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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rek
    -0.08
    continental
    -0.07
    *M
    -0.07
     avi
    -0.07
     Regents
    -0.06
    .camel
    -0.06
    /Q
    -0.06
     trance
    -0.06
    oring
    -0.06
     TZ
    -0.06
    POSITIVE LOGITS
    icide
    0.07
     edilmiş
    0.06
    uyệ
    0.06
    grounds
    0.06
    anchors
    0.06
     från
    0.06
    Bitcoin
    0.06
     JOIN
    0.06
    ,’
    0.06
     */}↵
    0.06
    Act Density 0.092%

    No Known Activations