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

    Neuronpedia

    INDEX
    Explanations

    and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     latter
    1.16
    Alternatively
    1.15
    either
    1.05
     either
    1.02
     Alternatively
    1.00
    @",
    0.98
    स्पर
    0.90
    Either
    0.90
    ജെ
    0.90
    بالإنجليزية
    0.88
    POSITIVE LOGITS
     and
    5.59
     và
    4.81
    และ
    4.73
     और
    4.52
     и
    4.49
     এবং
    4.43
     และ
    4.36
     आणि
    4.34
     και
    4.33
    and
    4.16
    Act Density 10.245%

    No Known Activations