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

    Neuronpedia

    INDEX
    Explanations

    Python library instantiations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     څنګه
    0.44
    라운
    0.38
    ']):
    0.38
    ']=
    0.37
    లోని
    0.37
    ])*
    0.36
    .])
    0.36
    thebetter
    0.35
    /),
    0.35
    थियों
    0.35
    POSITIVE LOGITS
    ();
    0.49
     ();
    0.43
     (
    0.42
     ()
    0.40
     mental
    0.38
     cease
    0.37
    ()
    0.37
     vocab
    0.36
     soap
    0.36
     she
    0.35
    Act Density 0.013%

    No Known Activations