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

    Neuronpedia

    INDEX
    Explanations

    multi-class classification layouts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     राजांनी
    0.45
    tris
    0.41
    ্রান্ত
    0.41
    層
    0.40
    ヵ
    0.39
    Threat
    0.38
    Dump
    0.38
    トン
    0.38
    husband
    0.38
    夫妻
    0.38
    POSITIVE LOGITS
     Bxh
    0.44
     Latte
    0.42
    की
    0.40
     gzip
    0.36
     Focal
    0.35
     برش
    0.35
     isValid
    0.34
     pajama
    0.34
     निकट
    0.34
     خم
    0.34
    Act Density 0.004%

    No Known Activations