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

    Neuronpedia

    INDEX
    Explanations

    fantasy stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ebooks
    -0.07
    稱
    -0.06
    caler
    -0.06
     �
    -0.06
    ulen
    -0.06
    _US
    -0.06
     lays
    -0.06
    。当
    -0.06
     relaciones
    -0.06
    κτη
    -0.06
    POSITIVE LOGITS
    .opts
    0.06
    рован
    0.06
     έναν
    0.06
     SignUp
    0.06
     تلف
    0.06
     szy
    0.06
    ]*(
    0.06
    :function
    0.06
     threatened
    0.06
    .timedelta
    0.06
    Act Density 0.012%

    No Known Activations