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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prob
    -0.06
    juan
    -0.06
    ")]
    -0.06
    \Factories
    -0.06
    nome
    -0.06
    MB
    -0.06
     scams
    -0.06
     Prob
    -0.05
     Universidad
    -0.05
    톤
    -0.05
    POSITIVE LOGITS
    /releases
    0.07
     {}.
    0.07
     сколько
    0.06
     Marx
    0.06
     floating
    0.06
     Việt
    0.06
    :create
    0.06
    мі
    0.06
    ільки
    0.06
    ('');↵
    0.06
    Act Density 0.018%

    No Known Activations