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

    Neuronpedia

    INDEX
    Explanations

    initial setup is key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பயன்ப
    0.40
     应用
    0.40
     相关
    0.38
    の方
    0.38
     yoki
    0.38
     materiál
    0.37
     Anwendungen
    0.37
    词
    0.36
     अनुप्रयोग
    0.36
    üss
    0.36
    POSITIVE LOGITS
     ONLY
    0.44
     firstly
    0.44
     initially
    0.42
     ultra
    0.42
     છેલ્લા
    0.41
     Initially
    0.41
     настолько
    0.41
     extremadamente
    0.40
     крупные
    0.40
     large
    0.39
    Act Density 0.088%

    No Known Activations