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

    Neuronpedia

    INDEX
    Explanations

    organization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ī
    -0.06
    緊
    -0.06
    ixe
    -0.06
     Roku
    -0.06
     حقوق
    -0.06
    .cor
    -0.06
     coffin
    -0.06
    _prompt
    -0.06
     фон
    -0.06
    práv
    -0.06
    POSITIVE LOGITS
     behavioural
    0.07
     discern
    0.06
    ΕΚ
    0.06
     الإ
    0.06
    -mark
    0.06
    行业
    0.06
    ным
    0.06
    consider
    0.06
     attained
    0.06
     Rehabilitation
    0.06
    Act Density 0.048%

    No Known Activations