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
    oblin
    -0.07
    osterone
    -0.07
    평
    -0.07
    .FileWriter
    -0.07
    919
    -0.07
     Classics
    -0.07
    759
    -0.06
    967
    -0.06
     رض
    -0.06
     Rock
    -0.06
    POSITIVE LOGITS
     abs
    0.07
    (hero
    0.06
    ö
    0.06
     dom
    0.06
    ln
    0.06
     ث
    0.06
     пози
    0.06
     留
    0.06
     figure
    0.06
     شهری
    0.06
    Act Density 0.004%

    No Known Activations