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

    Neuronpedia

    INDEX
    Explanations

    retargeting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dick
    -0.08
     Blut
    -0.08
     proteins
    -0.08
     Robertson
    -0.08
     גוף
    -0.08
    adax
    -0.08
    'époque
    -0.07
     Hersteller
    -0.07
     Sinne
    -0.07
     Schweizer
    -0.07
    POSITIVE LOGITS
     afili
    0.08
    SER
    0.08
     remark
    0.08
     खात
    0.07
    -aware
    0.07
     मित्र
    0.07
     स्मार्ट
    0.07
     referrals
    0.07
    inned
    0.07
    eles
    0.07
    Act Density 0.002%

    No Known Activations