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

    Neuronpedia

    INDEX
    Explanations

    specifically advertising or generated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     další
    0.47
     absoluto
    0.45
     innings
    0.44
    بعد
    0.42
     kilómetros
    0.42
    "
    0.42
    प
    0.42
     الترك
    0.41
     físico
    0.41
    ្អ
    0.41
    POSITIVE LOGITS
     ৩
    0.56
     licences
    0.55
     licence
    0.47
     ні
    0.47
     privatization
    0.47
     Licence
    0.46
    USH
    0.46
    ਾਕ
    0.46
    </h3>
    0.45
    uster
    0.45
    Act Density 0.000%

    No Known Activations