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

    Neuronpedia

    INDEX
    Explanations

    network nodes and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     effectually
    0.39
     mejoras
    0.38
     hạn
    0.38
     Improves
    0.37
    toDouble
    0.37
     অনু
    0.37
    avidin
    0.37
     improves
    0.36
    기가
    0.36
    物が
    0.36
    POSITIVE LOGITS
    ربع
    0.40
    脸
    0.39
     Lots
    0.38
    gra
    0.38
     Graz
    0.38
    Гра
    0.37
     kraja
    0.36
    cc
    0.36
    insert
    0.36
    ώσει
    0.36
    Act Density 0.000%

    No Known Activations