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

    Neuronpedia

    INDEX
    Explanations

    protocol

    np_max-act · gemini-2.0-flash

    structured data formats related to application deployment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Shak
    -0.08
    ünüz
    -0.07
    ünd
    -0.06
    itone
    -0.06
    .go
    -0.06
     sensor
    -0.06
     backButton
    -0.06
    AUTO
    -0.06
    的心
    -0.06
    $c
    -0.06
    POSITIVE LOGITS
     recomend
    0.09
     initialise
    0.07
    setQuery
    0.07
     massaggi
    0.07
     execute
    0.06
    arios
    0.06
    (cond
    0.06
    (Messages
    0.06
    (cfg
    0.06
     cryptography
    0.06
    Act Density 0.003%

    No Known Activations