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

    Neuronpedia

    INDEX
    Explanations

    dialogue turn indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forests
    0.43
    Requires
    0.40
     tonnage
    0.40
    調整
    0.39
     adjustments
    0.39
    字体
    0.39
     requires
    0.38
     profil
    0.38
     ਵਰ
    0.38
     structure
    0.38
    POSITIVE LOGITS
     কথোপকথ
    0.64
     Dialogue
    0.64
    对话
    0.56
     dialogue
    0.55
     dialogo
    0.55
     diálogo
    0.54
    dialog
    0.54
     Therapist
    0.53
     conversation
    0.52
     Gespräch
    0.51
    Act Density 0.042%

    No Known Activations