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

    Neuronpedia

    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash

    phrases related to safety and toxicity in chemical compounds.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Along
    -0.07
     improv
    -0.07
    aaa
    -0.07
    Sessions
    -0.07
     Walton
    -0.07
    NewProp
    -0.07
    など
    -0.06
    縣
    -0.06
     british
    -0.06
     horsepower
    -0.06
    POSITIVE LOGITS
    .setSize
    0.07
     ResultSet
    0.06
     filesystem
    0.06
     používá
    0.06
    PreparedStatement
    0.06
     ΣΤ
    0.06
    _into
    0.06
    .done
    0.05
     osobních
    0.05
    .asc
    0.05
    Act Density 0.302%

    No Known Activations