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

    Neuronpedia

    INDEX
    Explanations

    high school and fantasy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zarówno
    0.37
    為了
    0.36
     kisi
    0.35
     both
    0.34
     både
    0.34
     BECAUSE
    0.34
    ബ്രുവരി
    0.34
     subsection
    0.33
     Abschnitt
    0.33
    possessed
    0.33
    POSITIVE LOGITS
    High
    0.58
     High
    0.54
     हाई
    0.45
    Hight
    0.42
    high
    0.41
     高
    0.41
    HIGH
    0.40
     Hight
    0.38
    高
    0.38
    school
    0.38
    Act Density 0.025%

    No Known Activations