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

    Neuronpedia

    INDEX
    Explanations

    service quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یان
    1.22
    ی
    1.17
    卋
    1.13
    ை
    1.08
     aptly
    1.03
    కి
    1.03
    cotton
    0.98
    గొ
    0.98
    сус
    0.96
     dormant
    0.95
    POSITIVE LOGITS
    ológico
    1.05
     ಸಲ್ಲ
    1.02
    ום
    0.99
    t
    0.91
     बजा
    0.91
    ým
    0.90
    AuditEvent
    0.89
    भाव
    0.89
    KeyboardView
    0.88
    यह
    0.88
    Act Density 0.044%

    No Known Activations