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

    Neuronpedia

    INDEX
    Explanations

    kappa and eta symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exud
    0.41
     Chiron
    0.39
    FBSDKLogin
    0.38
    xcuser
    0.37
     leakage
    0.36
     dibujo
    0.36
    ClearedBy
    0.36
    ชน
    0.36
     चाहती
    0.35
     Sanford
    0.35
    POSITIVE LOGITS
     kappa
    1.58
     Kappa
    1.57
    kappa
    1.52
    Kappa
    1.44
     κ
    1.20
     kapp
    1.13
    κ
    1.11
     Kapp
    1.04
    0.95
     zeta
    0.87
    Act Density 0.002%

    No Known Activations