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

    Neuronpedia

    INDEX
    Explanations

    code terminators; or assignment endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.87
    ?")
    0.84
    ###
    0.83
    °)
    0.81
    0.79
    ?')
    0.78
    <unused152>
    0.78
    <unused2061>
    0.77
     Meanwhile
    0.77
    <unused1647>
    0.76
    POSITIVE LOGITS
    );
    1.68
    ;
    1.66
    ];
    1.62
    ";
    1.56
    ';
    1.49
    ；
    1.47
    ؛
    1.46
    !";
    1.41
    !;
    1.40
    };
    1.39
    Act Density 0.439%

    No Known Activations