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

    Neuronpedia

    INDEX
    Explanations

    plot function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ারের
    0.52
    ьте
    0.50
     getInstance
    0.48
    ように
    0.48
     gratification
    0.47
    රක
    0.46
    -\{
    0.46
    లుగు
    0.45
    ∈
    0.45
    вил
    0.44
    POSITIVE LOGITS
     fray
    0.46
    Drone
    0.45
    Artist
    0.45
    <0x0D>
    0.43
    Tucker
    0.43
     phir
    0.41
     шанс
    0.41
     ils
    0.40
    ك
    0.40
    <0x0C>
    0.40
    Act Density 0.018%

    No Known Activations