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

    Neuronpedia

    INDEX
    Explanations

    trying to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     choker
    0.57
     মুক্তিবাহিনীর
    0.55
     direktor
    0.55
    一系列
    0.55
     emblematic
    0.55
     spokeswoman
    0.54
    chyn
    0.53
     Valentin
    0.53
    edown
    0.53
    .³
    0.52
    POSITIVE LOGITS
    0.54
     список
    0.45
    ικό
    0.44
     Appro
    0.43
     université
    0.43
     giấc
    0.42
     tràn
    0.40
     угол
    0.38
    Э
    0.38
     gioc
    0.38
    Act Density 0.000%

    No Known Activations