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

    Neuronpedia

    INDEX
    Explanations

    listing conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =[-
    0.80
    ાર્થી
    0.75
    ில
    0.74
     फरक
    0.73
     మాత్రం
    0.72
    ൊന്നും
    0.69
    istir
    0.69
     extraer
    0.69
    }}=
    0.68
    crossentropy
    0.68
    POSITIVE LOGITS
    以及
    3.78
     sowie
    3.68
     plus
    3.61
     serta
    3.52
     以及
    3.48
     samt
    3.29
     oraz
    3.29
     aswell
    3.21
     sekä
    3.13
     وكذلك
    3.02
    Act Density 0.443%

    No Known Activations