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

    Neuronpedia

    INDEX
    Explanations

    bold and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    áveis
    0.89
    ความ
    0.81
    ered
    0.76
    onne
    0.71
    ess
    0.70
    บ้าง
    0.69
    eres
    0.69
    nons
    0.69
     зер
    0.69
     সন
    0.68
    POSITIVE LOGITS
     bahkan
    2.29
     Bahkan
    2.20
     sogar
    2.19
     zelfs
    2.15
     навіть
    2.14
     EVEN
    2.06
     even
    2.05
     addirittura
    2.03
     даже
    2.02
     حتی
    2.02
    Act Density 0.735%

    No Known Activations