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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QueryBuilder
    -0.07
     networking
    -0.07
     disagreements
    -0.07
    gres
    -0.06
    urator
    -0.06
    .usuario
    -0.06
     вероят
    -0.06
    γεν
    -0.06
     specificity
    -0.06
     Pry
    -0.06
    POSITIVE LOGITS
    rubu
    0.07
    Decre
    0.07
     dedim
    0.06
    exam
    0.06
     δια
    0.06
    AZ
    0.06
    .telegram
    0.06
     المق
    0.06
    (handles
    0.06
    読
    0.06
    Act Density 0.008%

    No Known Activations