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

    Neuronpedia

    INDEX
    Explanations

    you or someone you know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),
    0.38
    除
    0.38
    );
    0.38
    <h2>
    0.37
     parameter
    0.36
    )
    0.36
    ).
    0.36
     =>
    0.36
    owy
    0.36
    un
    0.35
    POSITIVE LOGITS
     others
    0.80
     his
    0.70
     অন্যরা
    0.69
     friends
    0.66
     colleagues
    0.63
     jego
    0.63
     whoever
    0.63
     collaborators
    0.61
     అతని
    0.61
     त्याच्या
    0.60
    Act Density 0.019%

    No Known Activations