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

    Neuronpedia

    INDEX
    Explanations

    it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.13
    ਰ
    0.84
    И
    0.82
    ప్ర
    0.77
    Após
    0.77
    ποιή
    0.77
    о
    0.76
    Η
    0.75
    خاذ
    0.75
    证券
    0.74
    POSITIVE LOGITS
     caj
    1.07
     cariño
    1.07
     decadent
    1.05
     dulce
    0.99
     другой
    0.99
     nube
    0.98
     decir
    0.96
     bueno
    0.96
     synaptic
    0.96
     dioses
    0.96
    Act Density 0.000%

    No Known Activations