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

    Neuronpedia

    INDEX
    Explanations

    generating lists and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кого
    0.33
    joyed
    0.32
    𒊒
    0.32
    도를
    0.31
    ный
    0.31
    फाली
    0.30
    tiny
    0.29
     infallible
    0.29
     insane
    0.29
     මෙම
    0.28
    POSITIVE LOGITS
     below
    0.50
     Below
    0.41
    Below
    0.41
    下面
    0.38
    below
    0.37
     abaixo
    0.35
     aşağı
    0.34
     bec
    0.33
     regarding
    0.32
     लक्षण
    0.32
    Act Density 0.031%

    No Known Activations