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

    Neuronpedia

    INDEX
    Explanations

    chess moves and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ë
    0.39
     థ
    0.38
     чувства
    0.38
    tube
    0.37
    欢
    0.36
    ைட்
    0.36
     近
    0.36
    으로서
    0.35
     memorials
    0.34
    Memorial
    0.34
    POSITIVE LOGITS
    विण्यात
    0.41
    termilk
    0.40
     Benedict
    0.39
     amni
    0.38
     insolvency
    0.38
    𓏸
    0.38
     weapon
    0.37
     ORGAN
    0.36
    Bernard
    0.36
     showcased
    0.36
    Act Density 0.000%

    No Known Activations