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

    Neuronpedia

    INDEX
    Explanations

    random choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FAT
    -0.07
    箱子
    -0.07
    .spacing
    -0.07
     개인정보
    -0.07
    _phi
    -0.07
    _units
    -0.07
    chi
    -0.07
    DNS
    -0.07
    当地时间
    -0.06
    SenderId
    -0.06
    POSITIVE LOGITS
    essage
    0.07
    CrLf
    0.06
     be
    0.06
    tığ
    0.06
    _ATTR
    0.06
    .crm
    0.06
    цу
    0.06
    뾰
    0.06
    があ
    0.06
     أع
    0.06
    Act Density 0.053%

    No Known Activations