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

    Neuronpedia

    INDEX
    Explanations

    HTML elements and CSS properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     résult
    0.31
     préféré
    0.30
     ബാറ്റ
    0.29
     charakter
    0.29
     kemenangan
    0.29
     amplit
    0.29
    VSLU
    0.29
     désir
    0.28
     Bedürfn
    0.28
     esigen
    0.28
    POSITIVE LOGITS
    _
    0.31
      
    0.28
    s
    0.26
     -
    0.25
    oline
    0.25
    у
    0.25
    \
    0.25
    c
    0.24
    d
    0.24
    x
    0.24
    Act Density 0.127%

    No Known Activations