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

    Neuronpedia

    INDEX
    Explanations

    time, means, late, final moments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    драт
    0.41
     ጥሩ
    0.40
     riego
    0.40
    tooltip
    0.39
    jelder
    0.39
     età
    0.38
     amel
    0.38
    telling
    0.37
     തമ്മ
    0.37
    âge
    0.37
    POSITIVE LOGITS
    payers
    0.37
    贵的
    0.36
     divisions
    0.35
    Мен
    0.35
    FUN
    0.35
    名的
    0.34
    WAYS
    0.34
    णारे
    0.33
    mo
    0.33
    READ
    0.33
    Act Density 0.000%

    No Known Activations