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

    Neuronpedia

    INDEX
    Explanations

    exploring relationships and positive experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     চালু
    0.42
     необхідно
    0.38
     allow
    0.38
     ensure
    0.35
     yield
    0.35
     regulatory
    0.35
     keep
    0.35
     additives
    0.35
     określ
    0.34
     knowledge
    0.34
    POSITIVE LOGITS
     struggles
    0.60
     struggle
    0.58
     experiences
    0.54
    experiences
    0.53
     kehidupan
    0.52
     journey
    0.48
    stru
    0.48
     experiencias
    0.48
     expériences
    0.48
     अनुभवों
    0.48
    Act Density 0.348%

    No Known Activations