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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нею
    -0.07
     fors
    -0.07
     terms
    -0.06
     memorandum
    -0.06
     summoned
    -0.06
     sat
    -0.06
     aun
    -0.06
     ineff
    -0.06
     dragged
    -0.06
     cual
    -0.06
    POSITIVE LOGITS
     delicate
    0.07
     Heller
    0.06
     Север
    0.06
     شن
    0.06
    ipc
    0.06
    .Std
    0.06
     peptides
    0.06
     AsyncCallback
    0.06
     Func
    0.06
    	restore
    0.06
    Act Density 0.000%

    No Known Activations