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

    Neuronpedia

    INDEX
    Explanations

    some or a few items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apapun
    0.88
     कोणत्याही
    0.72
     volled
    0.70
    基本的に
    0.69
     özelliği
    0.69
    duh
    0.68
     slightest
    0.67
     كامل
    0.67
    ∵
    0.66
     vollständig
    0.66
    POSITIVE LOGITS
     some
    5.67
    some
    4.87
     Some
    4.70
    Some
    4.70
    一些
    4.52
     بعض
    4.36
     algunos
    4.27
     alguns
    4.21
     algunas
    4.20
     einige
    4.14
    Act Density 1.246%

    No Known Activations