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

    Neuronpedia

    INDEX
    Explanations

    disease symptoms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    auction
    -0.07
    ↵↵↵↵↵↵↵
    -0.06
    _PACKET
    -0.06
     toilets
    -0.06
     Ζ
    -0.06
     Luz
    -0.06
     आम
    -0.06
    Value
    -0.06
     robust
    -0.06
     کامل
    -0.06
    POSITIVE LOGITS
    нед
    0.07
    ného
    0.07
    üne
    0.06
     heading
    0.06
     istediğiniz
    0.06
    .det
    0.06
    gien
    0.06
    _'
    0.06
    Emergency
    0.06
    ebilirsiniz
    0.06
    Act Density 0.036%

    No Known Activations