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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "relevant" in various contexts

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

    relevant to specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.44
    MENAFN
    -0.38
    openSession
    -0.35
     modalità
    -0.32
     дописавши
    -0.30
     blessures
    -0.30
    DrawerToggle
    -0.30
    sproz
    -0.29
     اعت
    -0.29
     Injuries
    -0.29
    POSITIVE LOGITS
    Relevant
    0.88
     relevant
    0.85
     příslu
    0.83
    relevant
    0.82
     Relevant
    0.74
     invokingState
    0.73
     соответству
    0.69
    íslu
    0.69
     kasarigan
    0.68
     ilgili
    0.67
    Act Density 0.022%

    No Known Activations