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

    Neuronpedia

    INDEX
    Explanations

    numbers and qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inverse
    0.32
     convolution
    0.30
     mandrel
    0.30
     ictal
    0.29
     singularities
    0.29
     parametrization
    0.28
     worthless
    0.28
     hydrodynamic
    0.28
     patterns
    0.28
     quantification
    0.27
    POSITIVE LOGITS
    1
    0.45
        
    0.38
            
    0.37
    2
    0.32
    doc
    0.30
    OT
    0.30
    4
    0.30
       
    0.30
    ovember
    0.30
              
    0.29
    Act Density 0.147%

    No Known Activations