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

    Neuronpedia

    INDEX
    Explanations

    port, question marks, punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻥ
    1.61
    completely
    1.43
    ங்கிணை
    1.42
    пример
    1.31
    ిన
    1.28
    security
    1.28
    ến
    1.23
    moniker
    1.23
    詳しくは
    1.23
    वायरस
    1.20
    POSITIVE LOGITS
    ي
    1.69
    i
    1.40
    اً
    1.38
    yana
    1.37
    াত্ত
    1.37
    垍
    1.36
    𝑖
    1.34
    يء
    1.34
    𝑦
    1.32
    𝗶
    1.31
    Act Density 0.064%

    No Known Activations