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

    Neuronpedia

    INDEX
    Explanations

    snippets of code

    oai_token-act-pair · gemini-2.0-flash

    da

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Da
    -1.45
    Da
    -1.37
     da
    -1.34
    da
    -1.23
    DA
    -0.99
     DA
    -0.98
     Dan
    -0.81
    Да
    -0.77
     Да
    -0.75
    Dan
    -0.73
    POSITIVE LOGITS
     disambiguazione
    0.68
    
    0.61
    addGap
    0.59
    Приятного
    0.55
     themſelves
    0.54
    ślę
    0.54
    numerusform
    0.54
     reaſon
    0.52
    PMailer
    0.52
    engesch
    0.51
    Act Density 10.277%

    No Known Activations