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

    Neuronpedia

    INDEX
    Explanations

    Descriptions of creative works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Queue
    -0.06
    	pw
    -0.06
     Moral
    -0.06
    これ
    -0.06
    marks
    -0.06
    -role
    -0.06
    altitude
    -0.06
     Θ
    -0.06
    Observable
    -0.06
    	fp
    -0.06
    POSITIVE LOGITS
     PIXI
    0.07
    _PRESS
    0.07
    .snapshot
    0.07
     तरफ
    0.06
     |[
    0.06
     aan
    0.06
     fashioned
    0.06
     جام
    0.06
     indian
    0.06
    负
    0.06
    Act Density 0.035%

    No Known Activations