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

    Neuronpedia

    INDEX
    Explanations

    HTML/markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Recipe
    -0.07
     allocations
    -0.07
    .warning
    -0.06
     pounding
    -0.06
     headache
    -0.06
     skills
    -0.06
    ops
    -0.06
    _np
    -0.06
    bons
    -0.06
     Games
    -0.06
    POSITIVE LOGITS
     нас
    0.07
     축
    0.06
    ')));↵
    0.06
     حکومت
    0.06
     representa
    0.06
    ульта
    0.06
     для
    0.06
     سالم
    0.06
     dest
    0.06
     віднов
    0.06
    Act Density 0.050%

    No Known Activations