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

    Neuronpedia

    INDEX
    Explanations

    scientific/mathematical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stoi
    -0.08
     Sniper
    -0.07
     Stalin
    -0.07
     用户
    -0.07
     сайте
    -0.07
    逆行
    -0.06
     Vatican
    -0.06
     lorem
    -0.06
     التج
    -0.06
     stepping
    -0.06
    POSITIVE LOGITS
    atypes
    0.07
    Something
    0.07
     droit
    0.06
    ras
    0.06
    _parts
    0.06
    <Response
    0.06
    Cad
    0.06
    Concern
    0.06
    ƪ
    0.06
    ographies
    0.06
    Act Density 0.124%

    No Known Activations