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

    Neuronpedia

    INDEX
    Explanations

    recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     control
    -0.07
     helpless
    -0.07
    	L
    -0.07
    //@
    -0.07
    s
    -0.07
    _ARR
    -0.07
    .As
    -0.06
    _S
    -0.06
    rition
    -0.06
    >S
    -0.06
    POSITIVE LOGITS
     Yahoo
    0.06
     DRAW
    0.06
     recycled
    0.06
     ：
    0.06
    ")
↵
↵
    0.06
     soda
    0.06
     mig
    0.06
     Doll
    0.06
     Pharma
    0.06
     дит
    0.06
    Act Density 0.030%

    No Known Activations