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

    Neuronpedia

    INDEX
    Explanations

    substituting values into formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    协会
    0.59
    风格
    0.55
     iletişim
    0.55
     అభిమా
    0.54
    റിയി
    0.53
    ورٹی
    0.53
    巉
    0.53
    娱乐
    0.52
    联盟
    0.52
     négoci
    0.52
    POSITIVE LOGITS
     Substituting
    1.16
     substituting
    1.09
     substitution
    1.05
     substitute
    1.02
    Substituting
    1.01
     substituted
    0.95
     Substitute
    0.93
     calculations
    0.88
     substitutes
    0.87
     substitutions
    0.86
    Act Density 0.218%

    No Known Activations