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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mods
    -0.07
    адження
    -0.07
    .zone
    -0.07
     printk
    -0.06
     bots
    -0.06
     kapas
    -0.06
     解
    -0.06
    ्यव
    -0.06
     tonnes
    -0.06
    apot
    -0.06
    POSITIVE LOGITS
     inaugural
    0.07
     بيت
    0.07
     struck
    0.07
    وان
    0.06
    	min
    0.06
    pong
    0.06
    lg
    0.06
    LC
    0.06
     Chill
    0.06
     دارم
    0.06
    Act Density 0.007%

    No Known Activations