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

    Neuronpedia

    INDEX
    Explanations

    energy, branch, entry format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    游戏
    0.43
     ویڈیو
    0.42
     peel
    0.41
    Menurut
    0.41
    比赛
    0.41
     সমালো
    0.41
    Music
    0.41
    岳
    0.41
    认为
    0.40
    ForThe
    0.40
    POSITIVE LOGITS
    to
    0.46
    it
    0.46
     enrolled
    0.45
    erad
    0.45
     there
    0.44
     progenitor
    0.44
     to
    0.43
    te
    0.43
    restrict
    0.42
     ascendent
    0.42
    Act Density 0.010%

    No Known Activations