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

    Neuronpedia

    INDEX
    Explanations

    terms related to peer involvement and local contexts in interventions

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

    local closer direct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cyfarwyddwr
    -0.41
    IntoConstraints
    -0.41
    CloseOperation
    -0.38
     automatique
    -0.36
    Transkript
    -0.35
    ustain
    -0.35
    fortawesome
    -0.34
     المعيارى
    -0.33
     <",
    -0.32
     viață
    -0.32
    POSITIVE LOGITS
    Closer
    0.64
     Closer
    0.59
     direct
    0.53
     closer
    0.52
     local
    0.50
     directa
    0.48
     diretta
    0.48
    GraphicsUnit
    0.47
     Local
    0.47
     nearer
    0.47
    Act Density 0.111%

    No Known Activations