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

    Neuronpedia

    INDEX
    Explanations

    thoughts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     camera
    -0.07
    DBNull
    -0.07
     treatment
    -0.06
     monarchy
    -0.06
     Lens
    -0.06
     Milwaukee
    -0.06
     franchise
    -0.06
     currency
    -0.06
     land
    -0.06
     republik
    -0.06
    POSITIVE LOGITS
     thoughts
    0.24
     Thoughts
    0.17
     reflections
    0.07
    odings
    0.07
    _MSB
    0.06
    思考
    0.06
    capabilities
    0.06
    그래
    0.06
    Tom
    0.06
     Matth
    0.06
    Act Density 0.010%

    No Known Activations