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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’de
    -0.07
     χώ
    -0.07
    Console
    -0.06
     muscle
    -0.06
     bigot
    -0.06
    'nin
    -0.06
     ה
    -0.06
     leukemia
    -0.06
     BAM
    -0.06
     Welfare
    -0.06
    POSITIVE LOGITS
     vaccinated
    0.07
     floating
    0.07
     Compiled
    0.07
    .setResult
    0.06
     نسمة
    0.06
    等
    0.06
     này
    0.06
     specifications
    0.06
     hdf
    0.06
    recipient
    0.06
    Act Density 0.007%

    No Known Activations