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

    Neuronpedia

    INDEX
    Explanations

    English and foreign 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distinguir
    0.37
     bölümde
    0.33
     инг
    0.31
    ాలంటే
    0.31
     sajana
    0.30
    的力量
    0.30
     შესახებ
    0.30
    থমে
    0.30
     plaintiff
    0.30
    क्रमण
    0.30
    POSITIVE LOGITS
     and
    0.56
     &
    0.52
     và
    0.52
     और
    0.49
    and
    0.45
     και
    0.42
     এবং
    0.41
     અને
    0.41
    および
    0.40
     и
    0.39
    Act Density 0.296%

    No Known Activations