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

    Neuronpedia

    INDEX
    Explanations

    ByteBuffer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    活性炭
    -0.07
     usern
    -0.07
    ሾ
    -0.06
    샥
    -0.06
    干部队伍
    -0.06
    rb
    -0.06
    ตำแ
    -0.06
    setMessage
    -0.06
     decis
    -0.06
    ylland
    -0.06
    POSITIVE LOGITS
    forming
    0.08
    _WRITE
    0.07
    ystems
    0.07
    ложений
    0.07
    .sess
    0.07
    Sorted
    0.07
    initely
    0.06
    овая
    0.06
    _soc
    0.06
    angles
    0.06
    Act Density 0.003%

    No Known Activations