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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    運動
    -0.07
    izmet
    -0.06
    430
    -0.06
    recursive
    -0.06
     tự
    -0.06
    adioButton
    -0.06
    ีเด
    -0.06
    .bounds
    -0.06
    xhr
    -0.06
    Fat
    -0.06
    POSITIVE LOGITS
     Irish
    0.07
     спеці
    0.06
    lixir
    0.06
    **,
    0.06
     Nug
    0.06
    existing
    0.06
     вред
    0.06
     дитини
    0.06
     duplex
    0.06
    FN
    0.06
    Act Density 0.014%

    No Known Activations