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

    Neuronpedia

    INDEX
    Explanations

    graft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wat
    -0.07
     مثال
    -0.07
    ёл
    -0.07
     每
    -0.06
    узы
    -0.06
    `).
    -0.06
     représent
    -0.06
     alike
    -0.06
    oks
    -0.06
     тен
    -0.06
    POSITIVE LOGITS
    エ
    0.06
       ↵    ↵
    0.06
    Preferences
    0.06
     Schiff
    0.06
    .pointer
    0.06
    cup
    0.06
     supermarkets
    0.06
    	src
    0.06
    metry
    0.06
     devastated
    0.05
    Act Density 0.002%

    No Known Activations