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

    Neuronpedia

    INDEX
    Explanations

    dependency injection container

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鋲
    0.42
    헿
    0.40
    ป่วย
    0.39
     Swain
    0.39
    الة
    0.38
    umin
    0.37
     infrastructural
    0.37
     saints
    0.37
    ப்ர
    0.37
     لوبوي
    0.37
    POSITIVE LOGITS
     multi
    0.44
     whopping
    0.42
     manufactured
    0.39
     claim
    0.37
     set
    0.37
    ăm
    0.37
     Claim
    0.37
     multiple
    0.37
     cid
    0.37
    搪
    0.36
    Act Density 0.001%

    No Known Activations