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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embod
    -0.07
     zaw
    -0.07
     Moff
    -0.06
    फ
    -0.06
    tf
    -0.06
     đảm
    -0.06
     activation
    -0.06
     центра
    -0.06
     周
    -0.06
    周
    -0.06
    POSITIVE LOGITS
    Dire
    0.07
    �
    0.06
    ?>↵↵
    0.06
     Sie
    0.06
     /**<
    0.06
     директор
    0.06
    ImageData
    0.06
    );">↵
    0.06
     chooses
    0.06
     sentenced
    0.06
    Act Density 0.000%

    No Known Activations