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

    Neuronpedia

    INDEX
    Explanations

    two/three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (identity
    -0.06
    olocation
    -0.06
    LIMIT
    -0.06
     shipping
    -0.06
        
    -0.06
     कभ
    -0.06
    榜
    -0.06
    Declared
    -0.06
    líž
    -0.06
     cashier
    -0.06
    POSITIVE LOGITS
    iciencies
    0.07
    .con
    0.07
    =back
    0.06
    iod
    0.06
    orrh
    0.06
    act
    0.06
     BACK
    0.06
    rh
    0.06
     sexle
    0.06
    кування
    0.06
    Act Density 0.003%

    No Known Activations