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

    Neuronpedia

    INDEX
    Explanations

    passes and game pass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ků
    0.47
    قه
    0.47
    jing
    0.44
    ikus
    0.43
    筧
    0.42
    ಪು
    0.42
    బు
    0.42
    huile
    0.42
     മുതൽ
    0.41
    roleum
    0.41
    POSITIVE LOGITS
     Taxonomic
    0.50
    in
    0.49
     discovers
    0.49
    ना
    0.48
    人格
    0.47
     Zoho
    0.47
    お子
    0.47
     tenta
    0.47
     itr
    0.46
     dihasil
    0.46
    Act Density 0.012%

    No Known Activations