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

    Neuronpedia

    INDEX
    Explanations

    but only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    퓰
    0.52
     EXAMPLE
    0.46
     Exemple
    0.45
    ᕇ
    0.44
    豳
    0.44
     বাড়ীতে
    0.43
     exemple
    0.42
     Marking
    0.42
    👸
    0.42
     Sociology
    0.42
    POSITIVE LOGITS
    :
    0.43
    null
    0.42
    due
    0.40
     `
    0.39
    `
    0.39
     "
    0.38
    id
    0.38
    …
    0.38
     “
    0.38
     due
    0.38
    Act Density 0.000%

    No Known Activations