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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    references to wages and economic issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    modes
    -0.07
     Kv
    -0.06
    凌
    -0.06
     colder
    -0.06
    �
    -0.06
    ,string
    -0.06
     Vương
    -0.06
    �
    -0.06
     astronaut
    -0.06
     ê
    -0.06
    POSITIVE LOGITS
     servlet
    0.06
     dagen
    0.06
     banquet
    0.06
     wired
    0.06
    ?),
    0.06
     الخارج
    0.06
    _started
    0.06
    wner
    0.06
    .spawn
    0.06
     cresc
    0.06
    Act Density 0.067%

    No Known Activations