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

    Neuronpedia

    INDEX
    Explanations

    favor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ividad
    -0.07
    calling
    -0.07
    ın
    -0.07
    ню
    -0.06
    _devices
    -0.06
    ;,
    -0.06
    )",↵
    -0.06
     dětí
    -0.06
    ema
    -0.06
     Ramirez
    -0.06
    POSITIVE LOGITS
     Start
    0.07
    plt
    0.06
    บล
    0.06
    angent
    0.06
     whats
    0.06
    اصل
    0.06
     Sol
    0.06
    Clicked
    0.06
     αυ
    0.06
    .online
    0.06
    Act Density 0.004%

    No Known Activations