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

    Neuronpedia

    INDEX
    Explanations

    Academic philosophy papers

    np_max-act · gemini-2.0-flash

    phrases suggesting normative evaluations or judgments regarding human actions and beliefs.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Angus
    -0.07
    /Form
    -0.06
     Tags
    -0.06
     typeId
    -0.06
     QUERY
    -0.06
    .F
    -0.06
     Parade
    -0.06
    ائد
    -0.06
     Ui
    -0.06
     ford
    -0.06
    POSITIVE LOGITS
    ",$
    0.07
    hower
    0.07
    YLON
    0.06
    xFFFFFFFF
    0.06
     قرآن
    0.06
    .et
    0.06
    xffff
    0.06
    .jasper
    0.06
     ім
    0.06
     strokeLine
    0.06
    Act Density 0.028%

    No Known Activations