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

    Neuronpedia

    INDEX
    Explanations

    policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    weep
    -0.08
     �
    -0.08
    pars
    -0.08
    spent
    -0.08
    \[
    -0.08
     పాటు
    -0.08
    fortune
    -0.08
    traditional
    -0.08
     spoj
    -0.07
    aked
    -0.07
    POSITIVE LOGITS
     critérios
    0.12
     procedures
    0.12
     qanday
    0.11
     guidelines
    0.11
     policies
    0.11
     Procedures
    0.11
     rules
    0.11
     критер
    0.11
     Policies
    0.10
     Rules
    0.10
    Act Density 0.120%

    No Known Activations