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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surprised
    -0.07
     Peninsula
    -0.06
    clause
    -0.06
    ीए
    -0.06
    แหล
    -0.06
     parity
    -0.06
    _observer
    -0.06
     FAQ
    -0.06
     baseball
    -0.06
     soutěže
    -0.06
    POSITIVE LOGITS
    ANTITY
    0.08
    완
    0.06
    -items
    0.06
     onClose
    0.06
     embodiments
    0.06
    unci
    0.06
    олн
    0.06
    キング
    0.06
    (each
    0.06
     от
    0.06
    Act Density 0.001%

    No Known Activations