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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proti
    -0.07
    elerin
    -0.07
     palindrome
    -0.07
     употреб
    -0.07
    (string
    -0.06
     mente
    -0.06
    _PEER
    -0.06
     Asc
    -0.06
    ector
    -0.06
     ощ
    -0.06
    POSITIVE LOGITS
    '',
    0.07
    .Ab
    0.07
    _finalize
    0.06
    Maria
    0.06
     sandwich
    0.06
     captures
    0.06
     Dy
    0.06
     dispersion
    0.06
     yummy
    0.06
    -lang
    0.06
    Act Density 0.050%

    No Known Activations