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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     goof
    -0.07
     voz
    -0.06
    방
    -0.06
     muttered
    -0.06
    手机
    -0.06
    top
    -0.06
     ασ
    -0.06
    ‌ال
    -0.06
    vo
    -0.06
     =>$
    -0.06
    POSITIVE LOGITS
    )])↵↵
    0.07
     undermined
    0.07
     intelligent
    0.07
    ляется
    0.06
    atures
    0.06
     Lt
    0.06
    -terrorism
    0.06
    анія
    0.06
    _keys
    0.06
     constructor
    0.06
    Act Density 0.060%

    No Known Activations