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

    Neuronpedia

    INDEX
    Explanations

    Saving, copying, editing, types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และการ
    0.40
     бет
    0.36
     גי
    0.35
    ОВА
    0.34
    ער
    0.34
     автофо
    0.34
    𒊩
    0.34
    чат
    0.33
    น
    0.33
    Ꮷ
    0.33
    POSITIVE LOGITS
     i
    0.42
    ui
    0.41
     u
    0.39
     at
    0.38
     To
    0.38
     t
    0.37
     through
    0.37
     are
    0.37
     Company
    0.36
     to
    0.36
    Act Density 0.110%

    No Known Activations