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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dodge
    -0.07
     велик
    -0.07
     fairy
    -0.07
     Excellent
    -0.07
     хорошо
    -0.07
    팖
    -0.06
    淑
    -0.06
     communion
    -0.06
     architect
    -0.06
     Roth
    -0.06
    POSITIVE LOGITS
    jsx
    0.07
     aprend
    0.07
     respawn
    0.07
    ACHINE
    0.07
    	local
    0.07
    local
    0.07
     ListView
    0.07
    جه
    0.06
    	layer
    0.06
    OLE
    0.06
    Act Density 0.005%

    No Known Activations