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

    Neuronpedia

    INDEX
    Explanations

    conversation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interactions
    0.50
     action
    0.48
     interacting
    0.48
     chatting
    0.48
    interaction
    0.47
     interaction
    0.47
     Chat
    0.47
     ação
    0.47
     Interactions
    0.46
     interacted
    0.46
    POSITIVE LOGITS
     mellom
    0.59
     между
    0.58
     Between
    0.57
     between
    0.56
     antara
    0.56
     μεταξύ
    0.56
    Between
    0.55
     mellem
    0.55
     mellan
    0.54
     Turn
    0.52
    Act Density 0.007%

    No Known Activations