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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ============
    -0.06
    (currentUser
    -0.06
    his
    -0.06
    а�
    -0.06
    (pro
    -0.06
     lista
    -0.06
    指导
    -0.06
     버
    -0.06
    (real
    -0.06
     thresh
    -0.06
    POSITIVE LOGITS
    егда
    0.07
    .Override
    0.07
    _LENGTH
    0.07
    ЙЙ
    0.07
    ALCHEMY
    0.07
    merce
    0.06
     раск
    0.06
    SearchParams
    0.06
    .Exists
    0.06
     lut
    0.06
    Act Density 0.019%

    No Known Activations