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

    Neuronpedia

    INDEX
    Explanations

    closing curly brackets at the end of code blocks and plus signs that might be related to changes or additions in code

    oai_token-act-pair · gemini-2.0-flash

    +}

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ربای
    -0.54
     phận
    -0.52
     createSlice
    -0.50
     Hara
    -0.49
    DeleteBehavior
    -0.49
     sê
    -0.49
    chka
    -0.46
    繁
    -0.45
     anda
    -0.45
    HOSTS
    -0.45
    POSITIVE LOGITS
    NOPQRST
    0.73
    }*/
    0.71
     kasarigan
    0.70
    }*/
    0.69
    <bos>
    0.68
    Geplaatst
    0.66
    rungsseite
    0.65
     disambiguazione
    0.65
    };*/
    0.65
     '\\;'
    0.65
    Act Density 0.635%

    No Known Activations