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

    Neuronpedia

    INDEX
    Explanations

    list structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2222>
    0.38
     কাদের
    0.38
    相關文章
    0.34
     Vantage
    0.34
    ப்பட்ட
    0.34
     –
    0.33
     those
    0.33
    <unused2140>
    0.33
     coerc
    0.32
     şeyler
    0.32
    POSITIVE LOGITS
     استعمال
    0.41
    》《
    0.40
     Steak
    0.39
     Admittedly
    0.38
     denna
    0.37
    ⺠
    0.37
    [*][[
    0.36
     генерал
    0.35
    😚
    0.35
    maskedTextBox
    0.35
    Act Density 0.120%

    No Known Activations