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

    Neuronpedia

    INDEX
    Explanations

    shows comparison or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ą
    0.44
    囩
    0.44
     یہی
    0.43
    ıntı
    0.42
    elijk
    0.41
    سل
    0.41
    ada
    0.41
    arlı
    0.40
    л
    0.40
    ichi
    0.40
    POSITIVE LOGITS
     demonstra
    0.50
     muestran
    0.49
    *
    0.49
     dimost
    0.48
    '
    0.48
     demost
    0.47
     catap
    0.46
     tropas
    0.46
     demostrar
    0.46
     Enroll
    0.46
    Act Density 0.047%

    No Known Activations