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

    Neuronpedia

    INDEX
    Explanations

    father

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     directional
    -0.09
     Admiral
    -0.08
     Publisher
    -0.08
    Directional
    -0.07
     brig
    -0.07
     conveyor
    -0.07
    EOF
    -0.07
     toxic
    -0.07
     athe
    -0.07
    اق
    -0.07
    POSITIVE LOGITS
     निर्ध
    0.08
    kwaliteit
    0.08
    共同
    0.08
     (…)
    0.08
     निश्चित
    0.08
    cele
    0.08
    ी
    0.08
    zoeken
    0.08
     candidates
    0.08
    cake
    0.08
    Act Density 0.004%

    No Known Activations