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

    Neuronpedia

    INDEX
    Explanations

    Common English words/phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    둥
    -0.08
     tư
    -0.07
     sit
    -0.07
     Sit
    -0.06
    expect
    -0.06
    UIS
    -0.06
    .xpath
    -0.06
    avis
    -0.06
     Maritime
    -0.06
    ším
    -0.06
    POSITIVE LOGITS
    girls
    0.07
     بح
    0.06
    /power
    0.06
    	params
    0.06
    MN
    0.06
    ธน
    0.06
    .nc
    0.06
    .')
    0.06
    /em
    0.06
    =rand
    0.06
    Act Density 0.002%

    No Known Activations