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

    Neuronpedia

    INDEX
    Explanations

    listing professions or groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     symbolism
    0.38
     discoloration
    0.36
     SeekBar
    0.36
    样式
    0.35
    และการ
    0.35
     heatmap
    0.35
    标记
    0.34
     glistening
    0.34
     photometry
    0.33
     ellipsis
    0.33
    POSITIVE LOGITS
     politicians
    0.59
     policymakers
    0.58
     governo
    0.54
     accountants
    0.53
     politici
    0.52
     psychologists
    0.51
     lawyers
    0.50
     insurers
    0.50
     government
    0.50
     investors
    0.50
    Act Density 0.172%

    No Known Activations