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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     где
    -0.08
    (factor
    -0.08
    .with
    -0.07
    {i
    -0.06
    由于
    -0.06
    isodes
    -0.06
     mohlo
    -0.06
     emperor
    -0.06
     Với
    -0.06
     (~(
    -0.06
    POSITIVE LOGITS
    Move
    0.07
    0.07
    Encryption
    0.07
    -lived
    0.07
     pry
    0.07
    depends
    0.07
    see
    0.06
    Picture
    0.06
     пос
    0.06
    -ignore
    0.06
    Act Density 0.007%

    No Known Activations