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

    Neuronpedia

    INDEX
    Explanations

    completeness or lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Unsupported
    -0.06
     editorial
    -0.06
    替
    -0.06
     wannonce
    -0.06
     Pressure
    -0.06
     chromat
    -0.06
    BILE
    -0.06
     bure
    -0.06
    GetY
    -0.06
    “(
    -0.06
    POSITIVE LOGITS
    adian
    0.07
    ado
    0.06
    _tensor
    0.06
    评价
    0.06
     madrid
    0.06
    adians
    0.06
    ADO
    0.06
    yped
    0.06
     costo
    0.06
     quello
    0.06
    Act Density 0.010%

    No Known Activations