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

    Neuronpedia

    INDEX
    Explanations

    sequences and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Acting
    0.41
    *}
    0.40
     프로그램을
    0.40
    租
    0.39
    裘
    0.38
    列表
    0.37
     newList
    0.37
    డని
    0.37
     intitul
    0.36
    リスト
    0.36
    POSITIVE LOGITS
     demandes
    0.41
     criticisms
    0.40
    WhiteSpace
    0.38
     explan
    0.36
    ファスナー
    0.36
     explanations
    0.35
    ತ್ಮ
    0.35
     conveyed
    0.35
    GA
    0.34
    umus
    0.34
    Act Density 0.000%

    No Known Activations