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

    Neuronpedia

    INDEX
    Explanations

    phrases related to membership or affiliation within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    categories following "of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.43
     avoit
    -0.38
    MessageTagHelper
    -0.36
     JAKARTA
    -0.36
     pouvoit
    -0.35
    ntö
    -0.34
    esterno
    -0.34
     OMITBAD
    -0.34
     statues
    -0.33
    ningss
    -0.32
    POSITIVE LOGITS
    Portale
    0.60
    inSlope
    0.57
    extAlignment
    0.52
    بوابة
    0.52
    autoreleasepool
    0.50
     للمعارف
    0.49
    ########.
    0.48
    Panamoan
    0.48
    што
    0.48
    yntaxException
    0.48
    Act Density 0.021%

    No Known Activations