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

    Neuronpedia

    INDEX
    Explanations

    specific business roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘵
    0.85
    त
    0.81
    𝘸
    0.81
    𝘯
    0.78
    annonce
    0.73
     полный
    0.71
    𝘴
    0.70
    epoca
    0.70
     impossibile
    0.69
     agad
    0.69
    POSITIVE LOGITS
    سات
    0.66
    יות
    0.63
    ции
    0.62
    kund
    0.60
     Techn
    0.59
    ation
    0.59
     tide
    0.58
    ious
    0.56
    etric
    0.56
    mard
    0.56
    Act Density 0.210%

    No Known Activations