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

    Neuronpedia

    INDEX
    Explanations

    facts are to contribute to wrist identify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Content
    0.37
     dễ
    0.37
     mê
    0.36
     Easier
    0.36
     content
    0.36
    这点
    0.34
    ional
    0.34
     easier
    0.34
    Matching
    0.34
    arraf
    0.34
    POSITIVE LOGITS
     թվական
    0.44
    搐
    0.42
    𝕖
    0.42
    趄
    0.42
    MR
    0.40
     ไล
    0.40
    tait
    0.40
    avait
    0.40
     ajouter
    0.40
    FileName
    0.39
    Act Density 0.000%

    No Known Activations