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

    Neuronpedia

    INDEX
    Explanations

    Wilson

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    衣服
    -0.07
    สาร
    -0.07
     bal
    -0.06
     Make
    -0.06
     Cards
    -0.06
    	task
    -0.06
    Rated
    -0.06
     Pants
    -0.06
     valeur
    -0.06
    eddar
    -0.06
    POSITIVE LOGITS
    Wilson
    0.11
     Wilson
    0.10
    !*
    0.07
     Nixon
    0.07
    ystals
    0.07
    ixon
    0.07
     wis
    0.07
     Zone
    0.07
     preempt
    0.07
    _MESH
    0.07
    Act Density 0.003%

    No Known Activations