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

    Neuronpedia

    INDEX
    Explanations

    the public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anderen
    0.41
     Bun
    0.41
    遌
    0.40
     universally
    0.38
    Bun
    0.37
     Were
    0.36
    股份有限公司
    0.35
    Were
    0.35
     were
    0.35
    hire
    0.35
    POSITIVE LOGITS
    public
    0.67
     public
    0.63
     público
    0.55
    大众
    0.55
     Developer
    0.49
    developer
    0.49
     Öffentlichkeit
    0.48
     Público
    0.44
     पब्लिक
    0.44
     población
    0.43
    Act Density 0.010%

    No Known Activations