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

    Neuronpedia

    INDEX
    Explanations

    purpose/function marker "для"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lecturing
    0.53
    ৃদ্ধ
    0.53
    েশনে
    0.52
     နှင့်
    0.52
    oliberal
    0.52
    র্জাতিক
    0.52
    lected
    0.50
     devastated
    0.50
     schizophrenia
    0.50
    keiten
    0.48
    POSITIVE LOGITS
    П
    0.57
     Ко
    0.56
     Ма
    0.55
     Д
    0.54
    та
    0.53
     П
    0.53
    па
    0.53
     Т
    0.53
    Ма
    0.52
    п
    0.52
    Act Density 0.002%

    No Known Activations