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

    Neuronpedia

    INDEX
    Explanations

    world or place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ことが多い
    0.84
     dispersive
    0.73
    oretically
    0.70
    ST
    0.68
     brute
    0.67
     ejection
    0.66
     wiggle
    0.66
     Psi
    0.66
     SOM
    0.65
    ARIO
    0.64
    POSITIVE LOGITS
    م
    0.95
    м
    0.88
    С
    0.86
    ό
    0.80
    З
    0.80
    ang
    0.77
    أ
    0.76
    До
    0.76
    ிருந்த
    0.75
    ות
    0.75
    Act Density 0.284%

    No Known Activations