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

    Neuronpedia

    INDEX
    Explanations

    giving information or items to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agus
    0.39
     quedando
    0.38
    DeleteDialogOpen
    0.36
     kecuali
    0.35
     gepubliceerd
    0.34
     creando
    0.33
     convirt
    0.33
    )))
    0.32
    ))
    0.32
    from
    0.32
    POSITIVE LOGITS
     нам
    0.62
     вам
    0.62
     us
    0.54
     Ihnen
    0.53
     आपको
    0.52
     мне
    0.50
     a
    0.49
     Вам
    0.49
     ஒரு
    0.48
     an
    0.48
    Act Density 0.562%

    No Known Activations