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

    Neuronpedia

    INDEX
    Explanations

    deletion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Empire
    -0.07
     concerts
    -0.07
    	headers
    -0.07
    -phase
    -0.07
    Care
    -0.06
    UBLIC
    -0.06
    とも
    -0.06
     Canary
    -0.06
    	text
    -0.06
    care
    -0.06
    POSITIVE LOGITS
     سه
    0.07
    orge
    0.07
     EI
    0.06
     depr
    0.06
    -cmpr
    0.06
     deletion
    0.06
     duplication
    0.06
    ें
    0.06
    sí
    0.06
    (Void
    0.06
    Act Density 0.003%

    No Known Activations