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

    Neuronpedia

    INDEX
    Explanations

    9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    1.56
    बाजी
    1.27
    ła
    1.26
     อืม
    1.22
    मिला
    1.22
    enje
    1.19
    ties
    1.19
    lene
    1.19
     teorema
    1.18
     estre
    1.17
    POSITIVE LOGITS
    ый
    1.47
    𝚜
    1.35
    er
    1.32
    きた
    1.31
     Suggested
    1.27
    ج
    1.26
    م
    1.25
    ни
    1.25
    ης
    1.23
    frac
    1.22
    Act Density 0.083%

    No Known Activations