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

    Neuronpedia

    INDEX
    Explanations

    post

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ¦
    -0.07
     forecasts
    -0.07
    };
    -0.07
    ’:
    -0.07
    }},↵
    -0.07
    -0.07
    }");
↵
    -0.07
     Bride
    -0.07
     McN
    -0.07
     loops
    -0.06
    POSITIVE LOGITS
     تلفن
    0.07
    ‌ی
    0.06
    webs
    0.06
     tìm
    0.06
     apro
    0.06
    �
    0.06
    imageUrl
    0.06
     ایست
    0.06
    istrovství
    0.06
     reck
    0.06
    Act Density 0.001%

    No Known Activations