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
    intColor
    -0.07
    Directories
    -0.07
     Chambers
    -0.06
    Center
    -0.06
    Radius
    -0.06
    .encoder
    -0.06
     теперь
    -0.06
     GMO
    -0.06
    etect
    -0.06
     Coroutine
    -0.06
    POSITIVE LOGITS
     vampire
    0.07
     tane
    0.07
    TOKEN
    0.06
    /payment
    0.06
    -job
    0.06
    hub
    0.06
     MEM
    0.06
    攻
    0.06
    lys
    0.06
     cleaner
    0.06
    Act Density 0.081%

    No Known Activations