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

    Neuronpedia

    INDEX
    Explanations

    considered deprecated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    பூ
    0.39
    郑
    0.38
    izare
    0.37
    Beer
    0.37
    栝
    0.36
    apon
    0.36
    فاوت
    0.36
    Kam
    0.35
     BUN
    0.35
     భూ
    0.35
    POSITIVE LOGITS
    运输
    0.48
    運輸
    0.45
     підприєм
    0.44
    လဲ
    0.42
    RM
    0.40
    輿
    0.40
     purchasing
    0.39
     ट्रांसपोर्ट
    0.39
     پرس
    0.38
    㠱
    0.38
    Act Density 0.000%

    No Known Activations