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

    Neuronpedia

    INDEX
    Explanations

    ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    theorem
    0.96
    test
    0.95
    torque
    0.94
     तरह
    0.91
     ス
    0.91
     attire
    0.90
    tool
    0.89
     clarinet
    0.88
    tang
    0.87
     sauvegard
    0.86
    POSITIVE LOGITS
     Всё
    0.96
     Только
    0.93
    ikten
    0.92
    чный
    0.89
     Некоторые
    0.86
    чным
    0.83
     síntomas
    0.82
     किये
    0.81
     Также
    0.80
    đenje
    0.80
    Act Density 0.001%

    No Known Activations