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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	gen
    -0.07
    菝
    -0.07
     shampoo
    -0.07
     giov
    -0.07
    ogg
    -0.06
    IDs
    -0.06
     caul
    -0.06
     carbohydrate
    -0.06
    않
    -0.06
    겔
    -0.06
    POSITIVE LOGITS
     sts
    0.07
    进入
    0.07
    ألع
    0.07
    .smart
    0.06
    (COLOR
    0.06
    𨟠
    0.06
    -delay
    0.06
     .
    0.06
    -track
    0.06
    .security
    0.06
    Act Density 0.026%

    No Known Activations