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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clown
    -0.08
    uration
    -0.06
    efore
    -0.06
     confident
    -0.06
     Ř
    -0.06
    RIES
    -0.06
     Kh
    -0.06
    iye
    -0.06
    OF
    -0.06
    NN
    -0.06
    POSITIVE LOGITS
    ptal
    0.07
    	Duel
    0.07
    ACCESS
    0.06
     toolbar
    0.06
     mView
    0.06
    bill
    0.06
    Quote
    0.06
     prohibition
    0.06
    .Restrict
    0.06
     selection
    0.06
    Act Density 0.014%

    No Known Activations