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

    Neuronpedia

    INDEX
    Explanations

    different contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ográfico
    0.38
    吧
    0.38
    倏
    0.38
     тексту
    0.38
    ordum
    0.37
    亗
    0.36
     समकक्ष
    0.36
     caramelized
    0.35
     થી
    0.35
     தொடர்புடைய
    0.35
    POSITIVE LOGITS
    dirname
    0.50
    ревнова
    0.42
     BELL
    0.40
     gan
    0.40
    েক্টর
    0.39
     എന്ന
    0.39
    ZONE
    0.38
     sistema
    0.37
    region
    0.37
     hakk
    0.37
    Act Density 0.000%

    No Known Activations