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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    十佳
    -0.07
     Descriptor
    -0.07
     prote
    -0.07
    .connector
    -0.07
    修为
    -0.07
    -approved
    -0.07
    ں
    -0.07
     >>↵↵
    -0.06
    wchar
    -0.06
    笑笑
    -0.06
    POSITIVE LOGITS
     плит
    0.08
    EĞ
    0.07
    ㅔ
    0.07
    のか
    0.07
     clarification
    0.07
     cây
    0.07
     evacuation
    0.06
     �
    0.06
    	MD
    0.06
    ilitation
    0.06
    Act Density 0.001%

    No Known Activations