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

    Neuronpedia

    INDEX
    Explanations

    plans, scheduled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    möglichkeiten
    -0.08
    ennessee
    -0.08
    -0.07
    울
    -0.07
     herd
    -0.07
    ضايا
    -0.07
     окружа
    -0.07
    _where
    -0.07
     czego
    -0.07
    hatian
    -0.07
    POSITIVE LOGITS
     ursprünglich
    0.13
     מראש
    0.12
     originally
    0.12
    预计
    0.12
     originalmente
    0.12
     vorgesehen
    0.11
    Originally
    0.11
     예상
    0.10
     planned
    0.10
     forvent
    0.09
    Act Density 0.047%

    No Known Activations