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

    Neuronpedia

    INDEX
    Explanations

    "]."

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Status
    -0.07
     craftsmanship
    -0.06
    _party
    -0.06
     Unit
    -0.06
     fascination
    -0.06
     potion
    -0.06
    dez
    -0.06
     Yao
    -0.06
     Stephan
    -0.06
     Chand
    -0.06
    POSITIVE LOGITS
     voted
    0.06
     decency
    0.06
    _Response
    0.06
    ->{
    0.06
     '')
    0.06
    llib
    0.06
    Like
    0.06
     ''){↵
    0.06
    Perform
    0.06
     Heavenly
    0.06
    Act Density 0.010%

    No Known Activations