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

    Neuronpedia

    INDEX
    Explanations

    password and code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemberList
    0.36
    ⒏
    0.32
    ミル
    0.32
    🔼
    0.32
    ພ
    0.31
    鄴
    0.31
    社会
    0.31
    🔷
    0.31
    δά
    0.31
    нические
    0.30
    POSITIVE LOGITS
     teamTable
    0.28
     Jonathan
    0.28
     van
    0.28
    emat
    0.28
    ährend
    0.27
    hasOwnProperty
    0.27
     į
    0.27
     {*}
    0.27
     this
    0.26
    (_)
    0.26
    Act Density 0.411%

    No Known Activations