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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nage
    -0.08
    安全
    -0.08
    -packed
    -0.08
    BOOST
    -0.08
    nod
    -0.08
    enta
    -0.08
    ニ
    -0.08
     boost
    -0.08
    .bo
    -0.08
    boost
    -0.07
    POSITIVE LOGITS
     admitted
    0.09
     essentially
    0.08
     bahasa
    0.08
    194
    0.08
     ภาษา
    0.08
     admitting
    0.08
     մասին
    0.08
     Henrik
    0.08
     fungsi
    0.08
    ?):
    0.08
    Act Density 0.029%

    No Known Activations