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

    Neuronpedia

    INDEX
    Explanations

    expressions and discourses surrounding political loyalty and dissent

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

    alarm and distress signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guapos
    -0.38
     chi̍t
    -0.35
     journée
    -0.34
     telefónica
    -0.33
     colgantes
    -0.32
     mediodía
    -0.31
     guapo
    -0.30
     cordones
    -0.30
    rouvez
    -0.30
     colgante
    -0.30
    POSITIVE LOGITS
    AndEndTag
    0.80
     OMITBAD
    0.64
    WaitGroup
    0.57
     onAnimation
    0.57
     OnTrigger
    0.56
     Taktlose
    0.56
     oprot
    0.56
    TagMode
    0.54
    gni
    0.54
    InitVars
    0.53
    Act Density 0.101%

    No Known Activations