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

    Neuronpedia

    INDEX
    Explanations

    quoting and delimiting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })/
    1.56
    )/
    1.53
    }}/
    1.52
    ])/
    1.49
    ]/
    1.45
    ))/
    1.43
    }/
    1.42
     "/
    1.34
     '/
    1.31
    ")/
    1.30
    POSITIVE LOGITS
    '])[
    0.81
    "][
    0.81
    ("[
    0.79
     அத
    0.78
    ('[
    0.78
     প্রা
    0.74
    )[
    0.73
     brack
    0.71
     ನ್ಯಾಯ
    0.69
    Segoe
    0.67
    Act Density 0.341%

    No Known Activations