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

    Neuronpedia

    INDEX
    Explanations

    the followed by specifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })\
    0.40
     tzw
    0.38
     তথা
    0.35
    లోని
    0.33
    Lem
    0.33
    प्रा
    0.33
     ты
    0.32
    ך
    0.32
     રહે
    0.32
    が見
    0.32
    POSITIVE LOGITS
    ട്ടുണ്ട്
    0.36
     opponent
    0.35
    вого
    0.34
     useDispatch
    0.33
     defenseman
    0.33
     synapse
    0.33
    ansen
    0.33
    aminase
    0.33
     Kollegen
    0.32
     asymptote
    0.32
    Act Density 0.067%

    No Known Activations