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

    Neuronpedia

    INDEX
    Explanations

    presented the idea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     הב
    0.87
     Kotlin
    0.85
     Ku
    0.84
     Chern
    0.82
    ಟಿ
    0.81
     gut
    0.78
     Warriors
    0.77
     Chakra
    0.77
     ponder
    0.76
    áctica
    0.75
    POSITIVE LOGITS
    ين
    0.81
    ه
    0.71
    也是
    0.71
    總統
    0.69
    Dropped
    0.68
    हां
    0.68
     musik
    0.66
    عند
    0.66
    ljenje
    0.65
    請
    0.65
    Act Density 0.000%

    No Known Activations