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

    Neuronpedia

    INDEX
    Explanations

    sentence transition after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    connection
    0.56
    Connections
    0.55
    connections
    0.54
     connection
    0.53
     connections
    0.53
     conex
    0.53
    artic
    0.52
     conexión
    0.52
     Connections
    0.52
     articul
    0.51
    POSITIVE LOGITS
     ஜி
    0.40
     EG
    0.39
    시아
    0.38
     meneg
    0.38
     NKG
    0.38
    ichen
    0.38
     Beg
    0.38
     begging
    0.38
     chemotherapy
    0.38
     begged
    0.38
    Act Density 0.000%

    No Known Activations