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

    Neuronpedia

    INDEX
    Explanations

    schedules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    기의
    -0.07
     معمولا
    -0.07
     Directors
    -0.07
    STRUCT
    -0.07
    表
    -0.07
    ром
    -0.07
    ชร
    -0.07
    ова
    -0.06
    λη
    -0.06
    يكا
    -0.06
    POSITIVE LOGITS
    	then
    0.07
     Lenovo
    0.06
    total
    0.06
    .hit
    0.06
     zen
    0.06
     rele
    0.06
    _receipt
    0.06
    ’en
    0.06
     ByteArrayInputStream
    0.06
     tint
    0.06
    Act Density 0.116%

    No Known Activations