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

    Neuronpedia

    INDEX
    Explanations

    knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twig
    -0.07
    end
    -0.07
    onom
    -0.07
     bond
    -0.06
    abet
    -0.06
    께서
    -0.06
     lines
    -0.06
     award
    -0.06
     hitch
    -0.06
     line
    -0.06
    POSITIVE LOGITS
    �
    0.08
     �
    0.07
     zonder
    0.06
     ни
    0.06
    EventArgs
    0.06
    (Entity
    0.06
     tổn
    0.06
     sockaddr
    0.06
    erap
    0.06
     Серг
    0.05
    Act Density 0.026%

    No Known Activations