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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical objects in various contexts

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

    objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     îna
    -0.61
     keuntungan
    -0.50
     sementara
    -0.50
    estart
    -0.50
     operativa
    -0.49
     scă
    -0.49
     nač
    -0.48
     termurah
    -0.47
     turun
    -0.47
    Namara
    -0.47
    POSITIVE LOGITS
     objects
    0.85
     object
    0.84
     Objects
    0.79
     objets
    0.76
     Object
    0.75
     OBJECT
    0.74
     objet
    0.70
    GetObject
    0.70
    object
    0.66
     objetos
    0.66
    Act Density 0.016%

    No Known Activations