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

    Neuronpedia

    INDEX
    Explanations

    state abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Payment
    -0.07
    mapping
    -0.07
    /get
    -0.06
    иболее
    -0.06
     escaping
    -0.06
    -trained
    -0.06
    _probe
    -0.06
     cervical
    -0.06
    abs
    -0.06
    Assets
    -0.06
    POSITIVE LOGITS
     cosa
    0.07
     Vintage
    0.07
     SEARCH
    0.07
    POOL
    0.06
     vals
    0.06
     βά
    0.06
     []↵↵↵
    0.06
     []↵
    0.06
     долго
    0.06
     NavLink
    0.06
    Act Density 0.007%

    No Known Activations