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

    Neuronpedia

    INDEX
    Explanations

    noun + modal verb/verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.47
    <
    0.47
     ۳
    0.46
     ۴
    0.45
    riction
    0.44
     ۷
    0.44
    ria
    0.42
     lainnya
    0.42
    uffix
    0.42
     ۸
    0.41
    POSITIVE LOGITS
     ও
    0.53
     voiture
    0.52
     doenças
    0.52
     prenez
    0.52
     và
    0.51
     এমন
    0.51
     acteurs
    0.50
     અને
    0.49
     hanno
    0.49
     informé
    0.49
    Act Density 0.299%

    No Known Activations