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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia articles (lists)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autoComplete
    -0.08
     West
    -0.07
    Extreme
    -0.07
     Buen
    -0.07
    frica
    -0.07
    分享
    -0.07
    ppe
    -0.07
     onClose
    -0.07
     University
    -0.06
     conject
    -0.06
    POSITIVE LOGITS
    $b
    0.07
    علاقات
    0.07
    三百
    0.07
    泪
    0.06
     INA
    0.06
     dimensional
    0.06
    enerated
    0.06
    赁
    0.06
    גד
    0.06
    RESSED
    0.06
    Act Density 0.001%

    No Known Activations