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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obsessed
    -0.08
    NECT
    -0.07
     addicted
    -0.07
    	project
    -0.07
    _operator
    -0.06
    sizes
    -0.06
    ieder
    -0.06
     elf
    -0.06
     GameManager
    -0.06
    	count
    -0.06
    POSITIVE LOGITS
    -State
    0.06
    趣
    0.06
     землі
    0.06
    请求
    0.06
    .utcnow
    0.06
     системи
    0.06
    采购
    0.06
    켜
    0.06
    味
    0.06
     Tyr
    0.06
    Act Density 0.000%

    No Known Activations