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

    Neuronpedia

    INDEX
    Explanations

    region or data related texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blogs
    0.53
     affiliate
    0.52
     Blogs
    0.50
     There
    0.50
     blogging
    0.49
     छत
    0.49
     dach
    0.48
     calcular
    0.48
     reduces
    0.47
     menghub
    0.46
    POSITIVE LOGITS
    ї
    0.51
    ités
    0.46
    ao
    0.45
    资金
    0.44
    тора
    0.44
    توان
    0.43
    اوم
    0.43
    ہیں
    0.43
    en
    0.42
    t
    0.42
    Act Density 0.000%

    No Known Activations