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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating human emotions and relationships

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

    preceding third-person plural verbs

    np_acts-logits-general · gemini-2.0-flash

    people performing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.76
     متعلقه
    -0.57
    Datuak
    -0.57
    ValueStyle
    -0.55
    ResponseWriter
    -0.54
    存于互联网档案馆
    -0.54
     estekak
    -0.54
    UTELY
    -0.53
    脚注の使い方
    -0.53
     Numa
    -0.51
    POSITIVE LOGITS
     habet
    0.57
     appliquer
    0.54
     quæ
    0.53
     pratiquer
    0.49
     valgt
    0.48
    нти
    0.48
    reactstrap
    0.48
     nemlig
    0.47
    IList
    0.46
    InitVars
    0.46
    Act Density 0.051%

    No Known Activations