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

    Neuronpedia

    INDEX
    Explanations

    making decisions or mistakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     možnost
    0.49
    ពេល
    0.47
     Thời
    0.47
    Thời
    0.47
     ημέ
    0.47
    മേ
    0.46
     Förderung
    0.46
     penerapan
    0.46
     канторы
    0.46
     otrzym
    0.44
    POSITIVE LOGITS
     amends
    0.79
     inroads
    0.77
     mistakes
    0.72
     make
    0.65
     predictions
    0.63
     made
    0.61
     mistake
    0.61
     headway
    0.61
     decisions
    0.61
     strides
    0.61
    Act Density 0.092%

    No Known Activations