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

    Neuronpedia

    INDEX
    Explanations

    distribution of information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metast
    0.51
     necks
    0.44
     serial
    0.44
     freshness
    0.41
     pipeline
    0.39
     SERIAL
    0.39
     rene
    0.39
    VertexBuffer
    0.38
     SQL
    0.38
     sequel
    0.38
    POSITIVE LOGITS
    Distribution
    0.48
     распреде
    0.47
     Distribution
    0.45
    Allocation
    0.42
     $|\
    0.41
     Compound
    0.41
     ڈپاز
    0.41
     répartition
    0.40
    叠
    0.40
    vcn
    0.39
    Act Density 0.079%

    No Known Activations