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

    Neuronpedia

    INDEX
    Explanations

    executable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dou
    -0.07
     Countries
    -0.07
     datas
    -0.06
    _go
    -0.06
     farms
    -0.06
    fq
    -0.06
    ']}'
    -0.06
     Most
    -0.06
    ('?
    -0.06
    faith
    -0.06
    POSITIVE LOGITS
     teal
    0.07
    ereum
    0.06
    ebilirsiniz
    0.06
     conforme
    0.06
    (MethodImplOptions
    0.06
     centerpiece
    0.06
    IMAGE
    0.06
     nexus
    0.06
     laughs
    0.06
    pling
    0.06
    Act Density 0.014%

    No Known Activations