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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أهم
    -0.08
     isa
    -0.08
    berge
    -0.08
     مهم
    -0.07
     החש
    -0.07
    ±
    -0.07
     elit
    -0.07
     möglichst
    -0.07
     أهمية
    -0.07
    pere
    -0.07
    POSITIVE LOGITS
     pronunciation
    0.10
     �
    0.09
    語
    0.09
    力
    0.09
     spelling
    0.09
    -English
    0.09
     शब्द
    0.09
     frases
    0.08
     inglesa
    0.08
     transl
    0.08
    Act Density 0.028%

    No Known Activations