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

    Neuronpedia

    INDEX
    Explanations

    ca followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    1.11
    ын
    1.10
    ロ
    1.10
    ிர்
    1.08
    ê
    1.06
    ána
    1.06
     Э
    1.06
    á
    1.05
     пой
    1.04
    avec
    1.04
    POSITIVE LOGITS
    ibular
    1.46
    CTURE
    1.34
    Instance
    1.30
     semasa
    1.28
    ىلى
    1.26
    طاء
    1.25
    ̞
    1.25
    Paxos
    1.24
    JSONArray
    1.23
     ceasefire
    1.23
    Act Density 0.000%

    No Known Activations