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

    Neuronpedia

    INDEX
    Explanations

    async Task methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouge
    0.42
     Leone
    0.38
     соль
    0.38
     Lester
    0.38
    eda
    0.37
     Sheriff
    0.37
     zależności
    0.37
    var
    0.37
     সংকো
    0.37
     व्याकरण
    0.36
    POSITIVE LOGITS
    ㄓ
    0.40
    Behaviours
    0.37
    Value
    0.36
    úblic
    0.35
    სი
    0.35
    𝙲
    0.34
    غي
    0.34
    personalised
    0.34
    getvalue
    0.34
    बहु
    0.33
    Act Density 0.001%

    No Known Activations