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

    Neuronpedia

    INDEX
    Explanations

    Deep dive / comprehensive overview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     አይደ
    0.39
     وير
    0.39
    ESSION
    0.38
     cruises
    0.37
     hypotheses
    0.36
    فيذ
    0.36
     importation
    0.36
     lipca
    0.36
    ARRIVAL
    0.36
    遶
    0.36
    POSITIVE LOGITS
     Explained
    0.65
     Detailed
    0.56
     Anleitung
    0.55
     подробно
    0.55
     Guide
    0.52
     explained
    0.51
     detailed
    0.50
     상세
    0.48
     Comprehensive
    0.48
    Detailed
    0.46
    Act Density 0.020%

    No Known Activations