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

    Neuronpedia

    INDEX
    Explanations

    recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }
    -1.84
     {
    -1.55
    ignements
    -1.47
    ⻓
    -1.45
     \{
    -1.44
     $>
    -1.41
     овощи
    -1.41
    önster
    -1.39
     "../../../
    -1.38
     '"
    -1.38
    POSITIVE LOGITS
    </em>
    1.68
     that
    1.52
    でございます
    1.45
    ↵
    1.43
    さんです
    1.42
    .”
    1.41
     aimed
    1.41
    なんだけど
    1.41
     europé
    1.39
     says
    1.36
    Act Density 0.013%

    No Known Activations