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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تمر
    -0.07
     Shed
    -0.06
     skeptic
    -0.06
    UU
    -0.06
    consult
    -0.06
    bottom
    -0.06
    ottle
    -0.06
    ротив
    -0.06
    now
    -0.06
    (XML
    -0.06
    POSITIVE LOGITS
    .appcompat
    0.07
     es
    0.07
     adjustable
    0.07
    tah
    0.07
     <*>
    0.06
     stable
    0.06
    .env
    0.06
     prt
    0.06
    demo
    0.06
     Eğer
    0.06
    Act Density 0.004%

    No Known Activations