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

    Neuronpedia

    INDEX
    Explanations

    being authentic and good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strict
    0.56
    厳
    0.52
     কঠোর
    0.52
     strictly
    0.51
     strictest
    0.51
     formal
    0.50
     formalism
    0.50
     Strict
    0.49
     perfekt
    0.48
    严格
    0.48
    POSITIVE LOGITS
     authentic
    1.13
     Authentic
    1.08
    Authent
    1.03
     confident
    1.02
     autent
    0.99
     mindful
    0.98
     authenticity
    0.96
     Authent
    0.94
     authent
    0.93
     autént
    0.93
    Act Density 0.100%

    No Known Activations