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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    арх
    -0.07
    aria
    -0.07
    ragment
    -0.07
    EDA
    -0.06
     misdemeanor
    -0.06
    ιώ
    -0.06
     heroine
    -0.06
    ongodb
    -0.06
    romo
    -0.06
    лия
    -0.06
    POSITIVE LOGITS
    了
    0.07
    _accept
    0.07
    .decoder
    0.07
    ages
    0.07
     tentang
    0.06
    _hex
    0.06
    \Client
    0.06
     agrees
    0.06
    !.
    0.06
     accelerator
    0.06
    Act Density 0.028%

    No Known Activations