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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "";
↵
↵
    -0.08
     "",
↵
    -0.08
    名無し
    -0.08
     ""
↵
    -0.08
    ογ
    -0.07
    how
    -0.07
     "",
    -0.07
     διαφορε
    -0.07
    ңа
    -0.07
    ﾜ
    -0.07
    POSITIVE LOGITS
     with
    0.08
     području
    0.07
     determinadas
    0.07
    worthiness
    0.07
    pered
    0.07
    വുമായി
    0.07
     
↵↵
    0.07
     ทุก
    0.07
    
↵↵
    0.07
     

    0.06
    Act Density 31.460%

    No Known Activations