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

    Neuronpedia

    INDEX
    Explanations

    numerical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yen
    -0.07
     uncover
    -0.07
    _sender
    -0.07
     fid
    -0.07
     radi
    -0.06
     Scient
    -0.06
     chatt
    -0.06
     enclosure
    -0.06
    _bounds
    -0.06
     ms
    -0.06
    POSITIVE LOGITS
    eksiyon
    0.06
    ázky
    0.06
    .Border
    0.06
    užel
    0.06
    enderror
    0.06
    čku
    0.06
    。今
    0.06
    ース
    0.06
    <ArrayList
    0.06
     rewriting
    0.06
    Act Density 0.017%

    No Known Activations