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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ackle
    -0.07
    Structure
    -0.07
     vlast
    -0.06
     gasoline
    -0.06
     Lum
    -0.06
    行政
    -0.06
     candy
    -0.06
    .Action
    -0.06
     structure
    -0.06
     Sloven
    -0.06
    POSITIVE LOGITS
    \:
    0.07
     trope
    0.06
    ічна
    0.06
    OptionsMenu
    0.06
    ;';↵
    0.06
    -Shirt
    0.06
    enkins
    0.06
    _;
↵
    0.06
     '))↵
    0.06
     Sasha
    0.06
    Act Density 0.022%

    No Known Activations