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

    Neuronpedia

    INDEX
    Explanations

    common nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unrecognized
    0.45
    р
    0.42
     samping
    0.41
    ко
    0.41
     untitled
    0.40
    г
    0.40
    во
    0.40
    fclose
    0.39
    곁
    0.39
     возникает
    0.38
    POSITIVE LOGITS
     pundits
    0.49
     Özellikle
    0.49
    酆
    0.48
     OEMs
    0.48
    ONOM
    0.47
     กลุ่ม
    0.47
    については
    0.47
     creatives
    0.46
    ANSAS
    0.46
    ských
    0.46
    Act Density 0.006%

    No Known Activations