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

    Neuronpedia

    INDEX
    Explanations

    foreign language context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ລະ
    0.54
     стара
    0.45
     প্রচেষ্টা
    0.44
     стреми
    0.44
     scammers
    0.43
    積極
    0.43
     своё
    0.42
     निगरानी
    0.42
     системи
    0.42
     visualization
    0.41
    POSITIVE LOGITS
    pun
    0.46
     günstig
    0.45
    mb
    0.43
    de
    0.42
    eston
    0.41
    gre
    0.41
     kurzen
    0.41
     niedrig
    0.40
     marzo
    0.40
    gl
    0.40
    Act Density 0.011%

    No Known Activations