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

    Neuronpedia

    INDEX
    Explanations

    presented with explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ای
    0.45
    tsy
    0.43
    latego
    0.43
     addirittura
    0.42
    だから
    0.42
    ப்பதால்
    0.41
     derfor
    0.41
     zelfs
    0.40
     nedenle
    0.40
     miatt
    0.40
    POSITIVE LOGITS
     beserta
    0.83
     Presented
    0.65
     Along
    0.59
     along
    0.58
     Please
    0.58
     presented
    0.57
     compiled
    0.56
     wraz
    0.55
     Detailed
    0.53
     Descriptions
    0.53
    Act Density 0.034%

    No Known Activations