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

    Neuronpedia

    INDEX
    Explanations

    lists or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     explicando
    0.44
     explaining
    0.40
     utilizando
    0.39
     الفعل
    0.39
     gördüğünüz
    0.38
     criando
    0.37
     వివ
    0.37
    藐
    0.37
     Buh
    0.37
    icits
    0.37
    POSITIVE LOGITS
    -‘
    0.39
    ERCIAL
    0.38
     reff
    0.37
    Inset
    0.36
    irable
    0.36
    昶
    0.35
     ২৮
    0.35
    کات
    0.35
     fate
    0.34
    Fade
    0.34
    Act Density 0.000%

    No Known Activations