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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _intro
    -0.07
     Tong
    -0.06
     slots
    -0.06
    .arg
    -0.06
    restore
    -0.06
     داشته
    -0.06
     jar
    -0.06
    _PACK
    -0.06
    _first
    -0.06
    Slot
    -0.06
    POSITIVE LOGITS
     concentrating
    0.08
     rozhod
    0.06
    ेड
    0.06
     zveřej
    0.06
    oliday
    0.06
     karar
    0.06
    іп
    0.06
     مل
    0.06
    "){
↵
    0.06
    拍
    0.06
    Act Density 0.003%

    No Known Activations