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

    Neuronpedia

    INDEX
    Explanations

    byte string delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лкой
    0.40
     carénés
    0.39
    固
    0.39
    ⟫
    0.39
    strates
    0.39
     божомол
    0.38
     thoại
    0.38
     şunu
    0.38
    Rising
    0.38
    尼亚
    0.38
    POSITIVE LOGITS
     '':
    0.83
     "":
    0.81
    "":
    0.77
     '/':
    0.64
    };
    0.63
     '-':
    0.63
     '*':
    0.62
     '+':
    0.62
    }.
    0.60
    }).
    0.58
    Act Density 0.024%

    No Known Activations