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

    Neuronpedia

    INDEX
    Explanations

    soundtrack

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Joy
    -0.07
     lee
    -0.07
    岳
    -0.06
     Te
    -0.06
     inhibitors
    -0.06
    071
    -0.06
     ebony
    -0.06
     dru
    -0.06
    лях
    -0.06
    	pos
    -0.06
    POSITIVE LOGITS
     scandals
    0.07
    coal
    0.06
    Coal
    0.06
    存档备份
    0.06
    تم
    0.06
    altet
    0.06
     کمتر
    0.06
    ending
    0.06
    �
    0.06
     centuries
    0.06
    Act Density 0.003%

    No Known Activations