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

    Neuronpedia

    INDEX
    Explanations

    listing code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Và
    0.57
    örungen
    0.52
    旕
    0.50
     excitations
    0.50
    Cách
    0.50
    ്യ
    0.49
    và
    0.48
    тности
    0.48
    梏
    0.48
    嬠
    0.48
    POSITIVE LOGITS
     desktop
    0.55
     spring
    0.53
     web
    0.52
     payroll
    0.50
     shiny
    0.49
     transparent
    0.48
     monthly
    0.48
     transparency
    0.48
     literacy
    0.47
     level
    0.46
    Act Density 0.003%

    No Known Activations