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

    Neuronpedia

    INDEX
    Explanations

    changing trends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     employs
    -0.07
     pulse
    -0.07
    ลา
    -0.07
    �
    -0.06
     Smart
    -0.06
    riger
    -0.06
     includ
    -0.06
     monde
    -0.06
     questions
    -0.06
     lap
    -0.06
    POSITIVE LOGITS
    Searching
    0.06
     умовах
    0.06
     τε
    0.06
     Pale
    0.06
    proj
    0.06
    _System
    0.06
     볼
    0.06
    nj
    0.06
    (distance
    0.06
    >{!!
    0.06
    Act Density 0.388%

    No Known Activations