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

    Neuronpedia

    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .policy
    -0.07
    include
    -0.07
    μές
    -0.07
     немає
    -0.06
    ="[
    -0.06
     prohibits
    -0.06
    Ak
    -0.06
     ones
    -0.06
     콘
    -0.06
     zien
    -0.06
    POSITIVE LOGITS
     discriminator
    0.07
    enticator
    0.07
     inequality
    0.07
     �
    0.07
    .EntityFrameworkCore
    0.06
    Imp
    0.06
    惊
    0.06
    陶
    0.06
     варт
    0.06
     dimin
    0.06
    Act Density 0.066%

    No Known Activations