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

    Neuronpedia

    INDEX
    Explanations

    sentence end

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    если
    0.80
    例子
    0.73
     stockbild
    0.73
    Якщо
    0.72
    assume
    0.70
    _
    0.70
     każdym
    0.69
    например
    0.69
    如果我们
    0.69
    เหล่านี้
    0.68
    POSITIVE LOGITS
    ↵↵
    1.84
     While
    1.23
     Specifically
    1.21
     Despite
    1.20
     Here
    1.19
     Their
    1.16
     Unfortunately
    1.16
     Sadly
    1.15
     According
    1.14
     Several
    1.13
    Act Density 0.235%

    No Known Activations