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

    Neuronpedia

    INDEX
    Explanations

    mp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    认清
    -0.07
    .street
    -0.07
    派驻
    -0.07
    _PRINTF
    -0.07
    ߏ
    -0.07
    itbart
    -0.07
     messaging
    -0.07
    征
    -0.06
    tras
    -0.06
    ownt
    -0.06
    POSITIVE LOGITS
    (stat
    0.08
    فيل
    0.07
    inqu
    0.07
    :num
    0.07
    abox
    0.07
     Polynomial
    0.07
    地说
    0.07
    orias
    0.07
    your
    0.07
    нима
    0.07
    Act Density 0.001%

    No Known Activations