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

    Neuronpedia

    INDEX
    Explanations

    code syntax and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kaz
    0.81
    position
    0.80
     положение
    0.78
    ﺹ
    0.76
    coh
    0.73
    夻
    0.71
    polar
    0.71
    qe
    0.70
    enfant
    0.70
     положения
    0.70
    POSITIVE LOGITS
    و
    1.01
     boardroom
    0.75
    лися
    0.73
     clubhouse
    0.73
     outbreaks
    0.72
     intrusion
    0.71
     Cryptocurrency
    0.71
    ುತ್ತಿದ್ದ
    0.70
    总部
    0.68
     Contracts
    0.66
    Act Density 0.001%

    No Known Activations