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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (indent
    -0.07
    .beh
    -0.07
    conduct
    -0.07
    .der
    -0.07
    yah
    -0.06
     �
    -0.06
    Xã
    -0.06
     Church
    -0.06
     bugs
    -0.06
     PAD
    -0.06
    POSITIVE LOGITS
    ErrorResponse
    0.06
    erior
    0.06
     vodka
    0.06
     aussi
    0.06
    _Location
    0.06
     robotic
    0.06
    radient
    0.06
    _GC
    0.06
    mayacak
    0.06
    _sid
    0.06
    Act Density 0.023%

    No Known Activations