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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by 'and' or comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heritage
    0.45
     hanging
    0.43
     itp
    0.42
     Մ
    0.42
     uniquement
    0.40
     plays
    0.39
    也可以
    0.39
     संबंधी
    0.38
    或其他
    0.38
     march
    0.38
    POSITIVE LOGITS
     आणि
    1.52
     અને
    1.48
     and
    1.45
     এবং
    1.44
     और
    1.42
     và
    1.42
    และ
    1.40
     ਅਤੇ
    1.40
     και
    1.38
     и
    1.34
    Act Density 0.061%

    No Known Activations