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

    Neuronpedia

    INDEX
    Explanations

    specific demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     c
    0.46
     ta
    0.46
     phones
    0.44
     trabajos
    0.42
     borg
    0.42
     lua
    0.41
     theta
    0.41
     pacif
    0.41
     mrs
    0.40
     Rock
    0.40
    POSITIVE LOGITS
    י
    0.48
    gruppen
    0.47
    тельном
    0.46
    荤
    0.46
    дық
    0.46
    特
    0.46
    xlim
    0.45
    噰
    0.45
    extends
    0.45
    ട്ര
    0.45
    Act Density 0.002%

    No Known Activations