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

    Neuronpedia

    INDEX
    Explanations

    code and tables

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ـــ
    0.50
     ...,
    0.49
    ــ
    0.49
    0.48
    ­
    0.48
     ​​​​
    0.47
     grill
    0.46
     cosidd
    0.46
    <0xC2>
    0.45
    ‭
    0.45
    POSITIVE LOGITS
     }^{*}$
    0.47
    ويات
    0.47
    віда
    0.45
     -->'
    0.45
    aggio
    0.43
    }$')
    0.42
    య్యా
    0.41
    ństwo
    0.41
    ণ্ডল
    0.41
    ູບ
    0.41
    Act Density 0.429%

    No Known Activations