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

    Neuronpedia

    INDEX
    Explanations

    Loading or starting text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.35
     muitas
    0.31
     has
    0.31
     And
    0.30
     và
    0.29
     benefici
    0.29
     மற்றும்
    0.29
     contribuer
    0.29
     During
    0.28
     și
    0.28
    POSITIVE LOGITS
    ితే
    0.32
    Най
    0.29
    например
    0.28
     //-
    0.27
    Ін
    0.27
    ":(
    0.27
     например
    0.27
    ій
    0.27
    ума
    0.27
     হিন্দুর
    0.26
    Act Density 0.253%

    No Known Activations