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

    Neuronpedia

    INDEX
    Explanations

    list item bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     freezing
    0.43
     hetero
    0.41
     hasher
    0.40
    alt
    0.37
     players
    0.37
     wett
    0.37
    ">=</
    0.36
    askell
    0.36
     conduction
    0.36
     abge
    0.36
    POSITIVE LOGITS
    ニュース
    0.47
     Бүген
    0.46
     звезда
    0.46
     NEWS
    0.40
    essex
    0.40
    oday
    0.39
     ચો
    0.39
     berita
    0.39
     स्टार
    0.38
     தேர்
    0.38
    Act Density 0.000%

    No Known Activations