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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wordt
    -0.06
    liste
    -0.06
     زیرا
    -0.06
     пів
    -0.06
     Torch
    -0.06
     Better
    -0.06
    ickest
    -0.06
    .rectangle
    -0.06
     Kare
    -0.06
    Football
    -0.06
    POSITIVE LOGITS
     Dortmund
    0.07
     Claudia
    0.07
    _province
    0.07
     implications
    0.07
     kaf
    0.07
     {}",
    0.06
     '',
    0.06
     roy
    0.06
    ‌ال
    0.06
    окс
    0.06
    Act Density 0.000%

    No Known Activations