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

    Neuronpedia

    INDEX
    Explanations

    references to emotional states and expressions of loss or longing

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

    demonstratives followed by entity/location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interactiva
    -0.49
     colectiva
    -0.49
     valentín
    -0.47
     Fakten
    -0.46
     Verständnis
    -0.45
     Presidencia
    -0.43
    Caractéristiques
    -0.42
     sfeer
    -0.42
     informática
    -0.42
     Erwartungen
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.68
    OGND
    0.64
    Pherson
    0.46
    scriptcase
    0.46
    LookAnd
    0.46
     Cie
    0.45
    ActionButton
    0.45
    writeFieldEnd
    0.45
    createTextNode
    0.45
    BorderFactory
    0.44
    Act Density 0.072%

    No Known Activations