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

    Neuronpedia

    INDEX
    Explanations

    Informal conversational writing

    np_max-act · gemini-2.0-flash

    descriptions and instructions related to food preparation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Invitation
    -0.08
     عامة
    -0.07
    TECTION
    -0.07
     больше
    -0.07
     confront
    -0.06
     Monte
    -0.06
     Gian
    -0.06
    كور
    -0.06
    THING
    -0.06
     policeman
    -0.06
    POSITIVE LOGITS
    std
    0.07
    ahren
    0.06
    LETED
    0.06
     bekl
    0.06
    $ret
    0.06
    алась
    0.06
     nackte
    0.06
    *l
    0.06
    urn
    0.06
    (xi
    0.06
    Act Density 0.023%

    No Known Activations