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

    Neuronpedia

    INDEX
    Explanations

    paragraph symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    标志着
    -0.08
    同时也是
    -0.07
    (hex
    -0.07
    hz
    -0.07
    不断发展
    -0.07
     waged
    -0.07
     Tide
    -0.07
     umieję
    -0.07
     Craw
    -0.07
     excav
    -0.06
    POSITIVE LOGITS
    เธ
    0.09
    _ep
    0.08
    艨
    0.07
    ს
    0.07
    纺
    0.07
    𝙏
    0.07
    .Points
    0.07
    (can
    0.07
    棁
    0.07
    $f
    0.07
    Act Density 0.001%

    No Known Activations