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

    Neuronpedia

    INDEX
    Explanations

    War and battles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cido
    -0.07
     JO
    -0.06
     forearm
    -0.06
     grö
    -0.06
    /com
    -0.06
     goed
    -0.06
     pare
    -0.06
     Lie
    -0.06
     folks
    -0.06
     apl
    -0.06
    POSITIVE LOGITS
    ucking
    0.07
     meddling
    0.06
    _DIRECTORY
    0.06
    buckets
    0.06
    ·
    0.06
    τικές
    0.06
     setAddress
    0.06
     Virginia
    0.06
    andez
    0.06
    ích
    0.06
    Act Density 0.015%

    No Known Activations