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

    Neuronpedia

    INDEX
    Explanations

    person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EOS
    -0.09
     Starter
    -0.07
    _symbols
    -0.07
    ot
    -0.07
     Vuex
    -0.06
     survives
    -0.06
     Phones
    -0.06
     spreads
    -0.06
    igor
    -0.06
    라
    -0.06
    POSITIVE LOGITS
    	constexpr
    0.07
    复
    0.06
     jí
    0.06
    озвращает
    0.06
    (interval
    0.06
    .isActive
    0.06
    findOrFail
    0.06
     =>
    0.06
    ("*
    0.06
     नगर
    0.06
    Act Density 0.028%

    No Known Activations