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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    specific instances of sports-related controversies and doping allegations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Encoding
    -0.07
     Campbell
    -0.07
    -derived
    -0.07
    _circle
    -0.07
    Clean
    -0.06
    Smoke
    -0.06
     olacağ
    -0.06
    Consumer
    -0.06
     Dawson
    -0.06
     başta
    -0.06
    POSITIVE LOGITS
     �
    0.07
    rust
    0.06
     zb
    0.06
    ZY
    0.06
    lád
    0.06
     relied
    0.06
    +'\
    0.06
     dru
    0.06
     *\
    0.06
    ivol
    0.06
    Act Density 0.063%

    No Known Activations