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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thorace
    0.69
     abdom
    0.63
     Astronom
    0.62
     patip
    0.61
     ка
    0.60
     κα
    0.60
    啍
    0.59
     attham
    0.59
     liga
    0.57
     Astros
    0.57
    POSITIVE LOGITS
    RAL
    0.64
    K
    0.61
    К
    0.61
    en
    0.59
     di
    0.59
    線の
    0.58
    Q
    0.57
    Р
    0.57
    Swiss
    0.55
    ING
    0.53
    Act Density 0.073%

    No Known Activations