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

    Neuronpedia

    INDEX
    Explanations

    intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Cl
    -0.07
    Accessor
    -0.07
     certifications
    -0.07
     photographic
    -0.07
    随
    -0.06
    ーフ
    -0.06
    ге
    -0.06
    acute
    -0.06
    _can
    -0.06
    τό
    -0.06
    POSITIVE LOGITS
    (HaveOccurred
    0.07
     nj
    0.06
    greens
    0.06
     영어
    0.06
    %@",
    0.06
    効
    0.06
    little
    0.06
    (rank
    0.06
     described
    0.06
     crazy
    0.05
    Act Density 0.057%

    No Known Activations