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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     registers
    -0.07
     justice
    -0.06
    .oc
    -0.06
     puzzle
    -0.06
     بنابر
    -0.06
    .rule
    -0.06
    Cour
    -0.06
    =data
    -0.06
     ranch
    -0.06
     Float
    -0.06
    POSITIVE LOGITS
    voř
    0.07
     赤
    0.07
    yses
    0.07
    .week
    0.07
    ysl
    0.07
     busiest
    0.07
     thưởng
    0.06
    _tF
    0.06
    iliar
    0.06
    shipment
    0.06
    Act Density 0.002%

    No Known Activations