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

    Neuronpedia

    INDEX
    Explanations

    headlines/quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apture
    -0.07
    ेस
    -0.07
     transitional
    -0.07
    ersion
    -0.07
    ailed
    -0.07
    edl
    -0.06
    ITIZE
    -0.06
    -0.06
    sigma
    -0.06
    umd
    -0.06
    POSITIVE LOGITS
    bst
    0.07
    ictureBox
    0.07
    ıyorum
    0.07
     suiv
    0.07
     подроб
    0.06
    DataStream
    0.06
     including
    0.06
     meaning
    0.06
     coeffs
    0.06
     occup
    0.06
    Act Density 0.017%

    No Known Activations