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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verte
    -0.06
     sert
    -0.06
     Ug
    -0.06
     Genel
    -0.06
    τοι
    -0.06
    .Gen
    -0.06
     XIII
    -0.06
     volcan
    -0.06
     visto
    -0.06
    .activities
    -0.06
    POSITIVE LOGITS
     inventory
    0.07
     onViewCreated
    0.06
    (DATA
    0.06
    랫
    0.06
    _LOOP
    0.06
     Initiative
    0.06
    редел
    0.06
    ندق
    0.06
     avoided
    0.06
    ای
    0.06
    Act Density 0.026%

    No Known Activations