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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }]}\
    0.70
    }}=$
    0.64
    0.62
    }}:
    0.62
    }}}=
    0.61
    }}\\
    0.60
    hostname
    0.60
    ';...
    0.60
    hexyl
    0.60
    }]{
    0.60
    POSITIVE LOGITS
    apped
    0.61
     বঞ্চিত
    0.59
     मुस्लिम
    0.58
     শুরুতে
    0.58
    ாலும்
    0.57
     Pap
    0.57
     paréntesis
    0.56
     Pra
    0.55
    ,.
    0.55
     رابطه
    0.55
    Act Density 1.450%

    No Known Activations