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

    Neuronpedia

    INDEX
    Explanations

    company names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     love
    0.74
     card
    0.73
     circumstances
    0.73
     parking
    0.73
    ẹp
    0.72
     خراب
    0.71
     practice
    0.69
    आप
    0.69
    াব্দ
    0.69
    iful
    0.65
    POSITIVE LOGITS
    Statement
    0.90
     والع
    0.82
    atoti
    0.77
    屒
    0.76
     समेत
    0.76
    ';"+
    0.76
    㐱
    0.75
    <unused87>
    0.74
    țiunea
    0.74
     ši
    0.74
    Act Density 0.003%

    No Known Activations