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

    Neuronpedia

    INDEX
    Explanations

    talk about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sighting
    0.59
     printer
    0.56
     majestic
    0.56
     homozyg
    0.55
     tanıt
    0.55
     для
    0.54
     lysed
    0.54
     rear
    0.53
     bekerja
    0.52
     bagi
    0.52
    POSITIVE LOGITS
     conversación
    2.20
     conversations
    2.19
     conversation
    2.16
     discuss
    2.02
     Conversation
    2.02
     discussions
    1.96
     Discuss
    1.94
    discuss
    1.94
    Conversation
    1.94
     discussion
    1.93
    Act Density 0.442%

    No Known Activations