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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and parentheses in code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    javascript closing syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لينكات
    -0.50
    ⓧ
    -0.49
     avoient
    -0.45
    싶
    -0.43
     ainfi
    -0.41
    zulegen
    -0.41
     Administrativna
    -0.41
     noël
    -0.41
     väljer
    -0.41
    yaç
    -0.40
    POSITIVE LOGITS
     });
    1.50
     }));
    1.38
     });
    1.35
     }))
    1.24
     }).
    1.23
     };
    1.22
     }],
    1.13
     }),
    1.13
     };
    1.11
     },
    1.05
    Act Density 0.005%

    No Known Activations