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
    Grade
    -0.08
    records
    -0.07
     residing
    -0.07
    $a
    -0.07
    ometr
    -0.06
    Topic
    -0.06
    ewish
    -0.06
    .ModelAdmin
    -0.06
     Rx
    -0.06
    -profit
    -0.06
    POSITIVE LOGITS
    ό
    0.07
    报告
    0.07
    NG
    0.06
     عباس
    0.06
     accommod
    0.06
     남자
    0.06
    ูท
    0.06
     \↵
    0.06
     stringWith
    0.06
    -inc
    0.06
    Act Density 0.003%

    No Known Activations