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

    Neuronpedia

    INDEX
    Explanations

    Freedom

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     connect
    -0.08
     analyze
    -0.07
     interior
    -0.07
    Second
    -0.07
    	echo
    -0.07
     SAVE
    -0.06
     "\↵
    -0.06
    insert
    -0.06
     уд
    -0.06
    estimate
    -0.06
    POSITIVE LOGITS
     العربية
    0.07
    ーラ
    0.07
     رفتار
    0.07
    좋
    0.07
    óc
    0.06
    中國
    0.06
     куп
    0.06
    });
↵
↵
    0.06
    IBUT
    0.06
    ophobia
    0.06
    Act Density 0.003%

    No Known Activations