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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绻
    -0.07
    짚
    -0.07
    .hibernate
    -0.07
     zn
    -0.07
     yabancı
    -0.07
    뉴
    -0.06
    丝丝
    -0.06
     staring
    -0.06
    _constructor
    -0.06
    Vir
    -0.06
    POSITIVE LOGITS
    Rates
    0.08
    Db
    0.07
    socket
    0.07
    这套
    0.07
     Primary
    0.07
    OCKET
    0.07
    友
    0.07
     meses
    0.07
    finished
    0.07
    ły
    0.07
    Act Density 0.020%

    No Known Activations