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

    Neuronpedia

    INDEX
    Explanations

    Northern or Southern Hemisphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    н
    0.88
    ن
    0.80
    λει
    0.61
    ал
    0.60
    ин
    0.59
    ン
    0.59
     окружа
    0.58
     separación
    0.57
     échanc
    0.57
     heb
    0.56
    POSITIVE LOGITS
    !),
    0.55
     Prepared
    0.53
    )!
    0.52
    amboo
    0.52
     in
    0.52
    !)
    0.51
    *:
    0.51
     Thurs
    0.51
     Zombies
    0.51
    tsi
    0.51
    Act Density 0.001%

    No Known Activations