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

    Neuronpedia

    INDEX
    Explanations

    tables and images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     because
    0.47
    ɒ
    0.47
     convolutions
    0.46
     overclock
    0.46
    ↵
    0.46
    <td>
    0.43
     ע
    0.42
     כ
    0.42
     binge
    0.42
    Buddhist
    0.42
    POSITIVE LOGITS
    ્સ
    0.50
    ्राम
    0.46
    矛盾
    0.45
    ский
    0.44
     representando
    0.44
    서
    0.44
     concernant
    0.44
     signalé
    0.43
    幼児
    0.43
    وں
    0.43
    Act Density 0.003%

    No Known Activations