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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Material
    -0.07
    .Pop
    -0.06
     Wy
    -0.06
     Haven
    -0.06
    _POINT
    -0.06
    tank
    -0.06
    /Create
    -0.06
    [str
    -0.06
     inmates
    -0.06
     connectionString
    -0.06
    POSITIVE LOGITS
    edis
    0.07
     illness
    0.06
     prior
    0.06
     prosec
    0.06
    Missing
    0.06
    .stub
    0.06
     ποι
    0.06
    egt
    0.06
    agnar
    0.06
     پیام
    0.06
    Act Density 0.048%

    No Known Activations