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

    Neuronpedia

    INDEX
    Explanations

    Code/memory management

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plethora
    -0.07
     least
    -0.07
     surprising
    -0.06
     문자
    -0.06
     ニ
    -0.06
     ordinary
    -0.06
    �
    -0.06
     Kou
    -0.06
     which
    -0.06
     withhold
    -0.06
    POSITIVE LOGITS
    ();
↵
↵
↵
    0.07
    .”↵↵↵↵
    0.07
    ...↵↵↵↵
    0.07
    ()
↵
↵
↵
    0.07
     ModelRenderer
    0.07
    ;
↵
↵
↵
↵
    0.07
    );
↵
↵
↵
    0.06
     widen
    0.06
    +-+-
    0.06
     "#"
    0.06
    Act Density 0.085%

    No Known Activations