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

    Neuronpedia

    INDEX
    Explanations

    tracing with a finger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нан
    0.52
    ariyam
    0.49
     уч
    0.48
    adikan
    0.46
    utm
    0.46
     hải
    0.46
     đại
    0.46
     آہ
    0.46
    ambil
    0.44
     प्रवृत्ति
    0.44
    POSITIVE LOGITS
    För
    0.52
     decode
    0.48
    Dopo
    0.48
     merkle
    0.46
     nær
    0.44
     শরণার্থীর
    0.44
     decoding
    0.43
    Für
    0.43
     Für
    0.42
    Hemos
    0.42
    Act Density 0.000%

    No Known Activations