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

    Neuronpedia

    INDEX
    Explanations

    activities and interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     של
    0.37
    0
    0.36
    Publish
    0.36
    ของการ
    0.36
    G
    0.35
    Current
    0.35
    Context
    0.34
    Busy
    0.34
    Genuine
    0.34
     مبنی
    0.34
    POSITIVE LOGITS
     with
    0.40
     socializing
    0.38
     corporations
    0.38
     conversar
    0.37
     jogar
    0.37
     antico
    0.36
    กับ
    0.36
    场所
    0.36
     distractions
    0.36
     diversión
    0.35
    Act Density 0.128%

    No Known Activations