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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skull
    -0.07
     elemento
    -0.07
    ospel
    -0.07
    .ToBoolean
    -0.07
     spectrum
    -0.06
     Array
    -0.06
     Rock
    -0.06
    Life
    -0.06
     นาย
    -0.06
     words
    -0.06
    POSITIVE LOGITS
    isan
    0.07
    发出
    0.07
    In
    0.06
    (in
    0.06
     vì
    0.06
    居
    0.06
     inbox
    0.06
     delayed
    0.06
    createView
    0.06
    .CLIENT
    0.06
    Act Density 0.017%

    No Known Activations