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

    Neuronpedia

    INDEX
    Explanations

    online bookings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sand
    -0.06
    声を
    -0.06
    หม
    -0.06
     Stay
    -0.06
     partir
    -0.06
    .substring
    -0.06
     ohne
    -0.06
     om
    -0.06
     machen
    -0.06
    Packages
    -0.06
    POSITIVE LOGITS
    _FLUSH
    0.07
    가를
    0.07
    :name
    0.06
     WTO
    0.06
    .createSequentialGroup
    0.06
     Canadian
    0.06
    HANDLE
    0.06
    GH
    0.06
     counterparts
    0.06
    =headers
    0.06
    Act Density 0.009%

    No Known Activations