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

    Neuronpedia

    INDEX
    Explanations

    sentence boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.54
    0.46
     있는데요
    0.44
    ?
    0.42
    .;
    0.42
     boutique
    0.42
     ہے۔
    0.41
    ;.
    0.41
     curly
    0.40
     â
    0.40
    POSITIVE LOGITS
    olve
    0.46
    विश्वास
    0.44
    ).\\
    0.42
    ålet
    0.42
     nadzie
    0.41
     vidas
    0.41
    ពួកគេ
    0.41
     Teknologi
    0.41
    निमल
    0.40
     további
    0.40
    Act Density 0.003%

    No Known Activations